[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-ybayle--awesome-deep-learning-music":3,"tool-ybayle--awesome-deep-learning-music":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":81,"owner_twitter":82,"owner_website":83,"owner_url":84,"languages":85,"stars":94,"forks":95,"last_commit_at":96,"license":97,"difficulty_score":98,"env_os":99,"env_gpu":99,"env_ram":99,"env_deps":100,"category_tags":103,"github_topics":104,"view_count":125,"oss_zip_url":81,"oss_zip_packed_at":81,"status":16,"created_at":126,"updated_at":127,"faqs":128,"releases":159},460,"ybayle\u002Fawesome-deep-learning-music","awesome-deep-learning-music","List of articles related to deep learning applied to music","awesome-deep-learning-music 是一个专注于深度学习与音乐领域交叉研究的开源资源库，通过系统整理学术论文、技术报告和代码资源，为研究者提供一站式参考。它解决了音乐信息处理领域研究资料分散、检索成本高的问题，尤其针对音乐生成、音源分离、乐器识别等任务，覆盖从1988年至今的重要研究成果。\n\n该资源库适合人工智能、音乐技术领域的研究人员和开发者使用，尤其对需要跟踪前沿算法、验证模型效果的研究者具有较高价值。其独特优势在于提供结构化数据：每项研究均附带论文标题、PDF链接、代码地址，并通过表格和Bib文件格式呈现元数据，方便学术引用。项目还包含统计可视化模块，可直观展示研究趋势和热点分布。\n\n尽管项目当前处于无人维护状态，但作者保留了完整的技术文档和贡献指南，鼓励社区协作更新。对于开发者而言，这里不仅是文献检索工具，更是了解音乐AI技术演进脉络的窗口。普通用户若对AI音乐创作原理感兴趣，也可通过摘要部分获取基础认知。","⚠️ This repo is unmaintained. While the info are still relevant, contributions to keep it up to date are welcome! A good starting point are the articles referenced here: https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music\u002Fissues\u002F5\n\n\u003Cimg align=\"right\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_08523d25d5e6.png\">\n\n# Deep Learning for Music (DL4M) [![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome)\n\nBy [Yann Bayle](http:\u002F\u002Fyannbayle.fr\u002Fenglish\u002Findex.php) ([Website](http:\u002F\u002Fyannbayle.fr\u002Fenglish\u002Findex.php), [GitHub](https:\u002F\u002Fgithub.com\u002Fybayle)) from LaBRI ([Website](http:\u002F\u002Fwww.labri.fr\u002F), [Twitter](https:\u002F\u002Ftwitter.com\u002FlabriOfficial\u002F)), Univ. Bordeaux ([Website](https:\u002F\u002Fwww.u-bordeaux.fr\u002F), [Twitter](https:\u002F\u002Ftwitter.com\u002Funivbordeaux)), CNRS ([Website](http:\u002F\u002Fwww.cnrs.fr\u002F), [Twitter](https:\u002F\u002Ftwitter.com\u002FCNRS)) and SCRIME ([Website](https:\u002F\u002Fscrime.u-bordeaux.fr\u002F)).\n\n**TL;DR** Non-exhaustive list of scientific articles on deep learning for music: [summary](#dl4m-summary) (Article title, pdf link and code), [details](dl4m.tsv) (table - more info), [details](dl4m.bib) (bib - all info)\n\nThe role of this curated list is to gather scientific articles, thesis and reports that use deep learning approaches applied to music.\nThe list is currently under construction but feel free to contribute to the missing fields and to add other resources! To do so, please refer to the [How To Contribute](#how-to-contribute) section.\nThe resources provided here come from my review of the state-of-the-art for my PhD Thesis for which an article is being written.\nThere are already surveys on deep learning for [music generation](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.01620.pdf), [speech separation](https:\u002F\u002Farxiv.org\u002Fftp\u002Farxiv\u002Fpapers\u002F1708\u002F1708.07524.pdf) and [speaker identification](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FSeyed_Reza_Shahamiri\u002Fpublication\u002F319158024_Speaker_Identification_Features_Extraction_Methods_A_Systematic_Review\u002Flinks\u002F599e2816aca272dff12fdef1\u002FSpeaker-Identification-Features-Extraction-Methods-A-Systematic-Review.pdf).\nHowever, these surveys do not cover music information retrieval tasks that are included in this repository.\n\n## Table of contents\n\n- [DL4M summary](#dl4m-summary)\n- [DL4M details](#dl4m-details)\n- [Code without articles](#code-without-articles)\n- [Statistics and visualisations](#statistics-and-visualisations)\n- [Advices for reviewers of dl4m articles](#advices-for-reviewers-of-dl4m-articles)\n- [How To Contribute](#how-to-contribute)\n- [FAQ](#faq)\n- [Acronyms used](#acronyms-used)\n- [Sources](#sources)\n- [Contributors](#contributors)\n- [Other useful related lists](#other-useful-related-lists-and-resources)\n- [Cited by](#cited-by)\n- [License](#license)\n\n## DL4M summary\n\n| Year |  Articles, Thesis and Reports | Code |\n|------|-------------------------------|------|\n| 1988 | Neural net modeling of music | No |\n| 1988 | [Creation by refinement: A creativity paradigm for gradient descent learning networks](http:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?arnumber=23933) | No |\n| 1988 | A sequential network design for musical applications | No |\n| 1989 | [The representation of pitch in a neural net model of chord classification](http:\u002F\u002Fwww.jstor.org\u002Fstable\u002F3679550) | No |\n| 1989 | [Algorithms for music composition by neural nets: Improved CBR paradigms](https:\u002F\u002Fquod.lib.umich.edu\u002Fcgi\u002Fp\u002Fpod\u002Fdod-idx\u002Falgorithms-for-music-composition.pdf?c=icmc;idno=bbp2372.1989.044;format=pdf) | No |\n| 1989 | [A connectionist approach to algorithmic composition](http:\u002F\u002Fwww.jstor.org\u002Fstable\u002F3679551) | No |\n| 1994 | [Neural network music composition by prediction: Exploring the benefits of psychoacoustic constraints and multi-scale processing](http:\u002F\u002Fwww-labs.iro.umontreal.ca\u002F~pift6080\u002FH09\u002Fdocuments\u002Fpapers\u002Fmozer-music.pdf) | No |\n| 1995 | [Automatic source identification of monophonic musical instrument sounds](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F3622871_Automatic_source_identification_of_monophonic_musical_instrument_sounds) | No |\n| 1995 | [Neural network based model for classification of music type](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F514161\u002F) | No |\n| 1997 | [A machine learning approach to musical style recognition](http:\u002F\u002Frepository.cmu.edu\u002Fcgi\u002Fviewcontent.cgi?article=1496&context=compsci) | No |\n| 1998 | [Recognition of music types](https:\u002F\u002Fwww.ri.cmu.edu\u002Fpub_files\u002Fpub1\u002Fsoltau_hagen_1998_2\u002Fsoltau_hagen_1998_2.pdf) | No |\n| 1999 | [Musical networks: Parallel distributed perception and performance](https:\u002F\u002Fs3.amazonaws.com\u002Facademia.edu.documents\u002F3551783\u002F10.1.1.39.6248.pdf?AWSAccessKeyId=AKIAIWOWYYGZ2Y53UL3A&Expires=1507055806&Signature=5mGzQc7bvJgUZYfXOmCX8eeNQOs%3D&response-content-disposition=inline%3B%20filename%3DMusical_networks_Parallel_distributed_pe.pdf) | No |\n| 2001 | [Multi-phase learning for jazz improvisation and interaction](http:\u002F\u002Fwww.cs.smith.edu\u002F~jfrankli\u002Fpapers\u002FCtColl01.pdf) | No |\n| 2002 | [A supervised learning approach to musical style recognition](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FGiuseppe_Buzzanca\u002Fpublication\u002F228588086_A_supervised_learning_approach_to_musical_style_recognition\u002Flinks\u002F54b43ee90cf26833efd0109f.pdf) | No |\n| 2002 | [Finding temporal structure in music: Blues improvisation with LSTM recurrent networks](http:\u002F\u002Fwww-perso.iro.umontreal.ca\u002F~eckdoug\u002Fpapers\u002F2002_ieee.pdf) | No |\n| 2002 | [Neural networks for note onset detection in piano music](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FMatija_Marolt\u002Fpublication\u002F2473938_Neural_Networks_for_Note_Onset_Detection_in_Piano_Music\u002Flinks\u002F00b49525efccc79fed000000.pdf) | No |\n| 2004 | [A convolutional-kernel based approach for note onset detection in piano-solo audio signals](http:\u002F\u002Fwww.murase.nuie.nagoya-u.ac.jp\u002F~ide\u002Fres\u002Fpaper\u002FE04-conference-pablo-1.pdf) | No |\n| 2009 | [Unsupervised feature learning for audio classification using convolutional deep belief networks](http:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F3674-unsupervised-feature-learning-for-audio-classification-using-convolutional-deep-belief-networks.pdf) | No |\n| 2010 | [Audio musical genre classification using convolutional neural networks and pitch and tempo transformations](http:\u002F\u002Flbms03.cityu.edu.hk\u002Ftheses\u002Fc_ftt\u002Fmphil-cs-b39478026f.pdf) | No |\n| 2010 | [Automatic musical pattern feature extraction using convolutional neural network](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FAntoni_Chan2\u002Fpublication\u002F44260643_Automatic_Musical_Pattern_Feature_Extraction_Using_Convolutional_Neural_Network\u002Flinks\u002F02e7e523dac6bb86b0000000.pdf) | No |\n| 2011 | [Audio-based music classification with a pretrained convolutional network](http:\u002F\u002Fwww.ismir2011.ismir.net\u002Fpapers\u002FPS6-3.pdf) | No |\n| 2012 | [Rethinking automatic chord recognition with convolutional neural networks](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F6406762\u002F) | No |\n| 2012 | [Moving beyond feature design: Deep architectures and automatic feature learning in music informatics](http:\u002F\u002Fciteseerx.ist.psu.edu\u002Fviewdoc\u002Fdownload?doi=10.1.1.294.2304&rep=rep1&type=pdf) | No |\n| 2012 | [Local-feature-map integration using convolutional neural networks for music genre classification](http:\u002F\u002Fliris.cnrs.fr\u002FDocuments\u002FLiris-5602.pdf) | No |\n| 2012 | [Learning sparse feature representations for music annotation and retrieval](https:\u002F\u002Fpdfs.semanticscholar.org\u002F099d\u002F85f25e9336f48ff64287a4b53ee5fb64ab51.pdf) | No |\n| 2012 | [Unsupervised learning of local features for music classification](http:\u002F\u002Fwww.ismir2012.ismir.net\u002Fevent\u002Fpapers\u002F139_ISMIR_2012.pdf) | No |\n| 2013 | [Multiscale approaches to music audio feature learning](http:\u002F\u002Fismir2013.ismir.net\u002Fwp-content\u002Fuploads\u002F2013\u002F09\u002F69_Paper.pdf) | No |\n| 2013 | [Musical onset detection with convolutional neural networks](http:\u002F\u002Fphenicx.upf.edu\u002Fsystem\u002Ffiles\u002Fpublications\u002FSchlueter_MML13.pdf) | No |\n| 2013 | [Deep content-based music recommendation](http:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F5004-deep-content-based-music-recommendation.pdf) | No |\n| 2014 | [The munich LSTM-RNN approach to the MediaEval 2014 Emotion In Music task](https:\u002F\u002Fpdfs.semanticscholar.org\u002F8a24\u002Fc5131d5a28165f719697028c34b00e6d3f60.pdf) | No |\n| 2014 | [End-to-end learning for music audio](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F6854950\u002F) | No |\n| 2014 | [Deep learning for music genre classification](https:\u002F\u002Fcourses.engr.illinois.edu\u002Fece544na\u002Ffa2014\u002FTao_Feng.pdf) | No |\n| 2014 | [Recognition of acoustic events using deep neural networks](https:\u002F\u002Fwww.cs.tut.fi\u002Fsgn\u002Farg\u002Fmusic\u002Ftuomasv\u002Fdnn_eusipco2014.pdf) | No |\n| 2014 | [Deep image features in music information retrieval](https:\u002F\u002Fwww.degruyter.com\u002Fdownloadpdf\u002Fj\u002Feletel.2014.60.issue-4\u002Feletel-2014-0042\u002Feletel-2014-0042.pdf) | No |\n| 2014 | [From music audio to chord tablature: Teaching deep convolutional networks to play guitar](https:\u002F\u002Fejhumphrey.com\u002Fassets\u002Fpdf\u002Fhumphrey2014music.pdf) | No |\n| 2014 | [Improved musical onset detection with convolutional neural networks](http:\u002F\u002Fwww.mirlab.org\u002Fconference_papers\u002FInternational_Conference\u002FICASSP%202014\u002Fpapers\u002Fp7029-schluter.pdf) | No |\n| 2014 | [Boundary detection in music structure analysis using convolutional neural networks](https:\u002F\u002Fdav.grrrr.org\u002Fpublic\u002Fpub\u002Fullrich_schlueter_grill-2014-ismir.pdf) | No |\n| 2014 | [Improving content-based and hybrid music recommendation using deep learning](http:\u002F\u002Fwww.smcnus.org\u002Fwp-content\u002Fuploads\u002F2014\u002F08\u002Freco_MM14.pdf) | No |\n| 2014 | [A deep representation for invariance and music classification](http:\u002F\u002Fwww.mirlab.org\u002Fconference_papers\u002FInternational_Conference\u002FICASSP%202014\u002Fpapers\u002Fp7034-zhang.pdf) | No |\n| 2015 | [Auralisation of deep convolutional neural networks: Listening to learned features](http:\u002F\u002Fismir2015.uma.es\u002FLBD\u002FLBD24.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi\u002FAuralisation) |\n| 2015 | [Downbeat tracking with multiple features and deep neural networks](http:\u002F\u002Fperso.telecom-paristech.fr\u002F~grichard\u002FPublications\u002F2015-durand-icassp.pdf) | No |\n| 2015 | [Music boundary detection using neural networks on spectrograms and self-similarity lag matrices](http:\u002F\u002Fwww.ofai.at\u002F~jan.schlueter\u002Fpubs\u002F2015_eusipco.pdf) | No |\n| 2015 | [Classification of spatial audio location and content using convolutional neural networks](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FToni_Hirvonen\u002Fpublication\u002F276061831_Classification_of_Spatial_Audio_Location_and_Content_Using_Convolutional_Neural_Networks\u002Flinks\u002F5550665908ae12808b37fe5a\u002FClassification-of-Spatial-Audio-Location-and-Content-Using-Convolutional-Neural-Networks.pdf) | No |\n| 2015 | [Deep learning, audio adversaries, and music content analysis](http:\u002F\u002Fwww2.imm.dtu.dk\u002Fpubdb\u002Fviews\u002Fedoc_download.php\u002F6905\u002Fpdf\u002Fimm6905.pdf) | No |\n| 2015 | [Deep learning and music adversaries](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1507.04761.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fcoreyker\u002Fdnn-mgr) |\n| 2015 | [Singing voice detection with deep recurrent neural networks](https:\u002F\u002Fhal-imt.archives-ouvertes.fr\u002Fhal-01110035\u002F) | No |\n| 2015 | [Automatic instrument recognition in polyphonic music using convolutional neural networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1511.05520.pdf) | No |\n| 2015 | [A software framework for musical data augmentation](https:\u002F\u002Fbmcfee.github.io\u002Fpapers\u002Fismir2015_augmentation.pdf) | No |\n| 2015 | [A deep bag-of-features model for music auto-tagging](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1508.04999v1.pdf) | No |\n| 2015 | [Music-noise segmentation in spectrotemporal domain using convolutional neural networks](http:\u002F\u002Fismir2015.uma.es\u002FLBD\u002FLBD27.pdf) | No |\n| 2015 | [Musical instrument sound classification with deep convolutional neural network using feature fusion approach](https:\u002F\u002Farxiv.org\u002Fftp\u002Farxiv\u002Fpapers\u002F1512\u002F1512.07370.pdf) | No |\n| 2015 | [Environmental sound classification with convolutional neural networks](http:\u002F\u002Fkarol.piczak.com\u002Fpapers\u002FPiczak2015-ESC-ConvNet.pdf) | No |\n| 2015 | [Exploring data augmentation for improved singing voice detection with neural networks](https:\u002F\u002Fgrrrr.org\u002Fpub\u002Fschlueter-2015-ismir.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Ff0k\u002Fismir2015) |\n| 2015 | [Singer traits identification using deep neural network](https:\u002F\u002Fcs224d.stanford.edu\u002Freports\u002FSkiZhengshan.pdf) | No |\n| 2015 | [A hybrid recurrent neural network for music transcription](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1411.1623.pdf) | No |\n| 2015 | [An end-to-end neural network for polyphonic music transcription](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1508.01774.pdf) | No |\n| 2015 | [Deep karaoke: Extracting vocals from musical mixtures using a convolutional deep neural network](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-22482-4_50) | No |\n| 2015 | [Folk music style modelling by recurrent neural networks with long short term memory units](http:\u002F\u002Fismir2015.uma.es\u002FLBD\u002FLBD13.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FIraKorshunova\u002Ffolk-rnn) |\n| 2015 | [Deep neural network based instrument extraction from music](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FStefan_Uhlich\u002Fpublication\u002F282001406_Deep_neural_network_based_instrument_extraction_from_music\u002Flinks\u002F5600eeda08ae07629e52b397\u002FDeep-neural-network-based-instrument-extraction-from-music.pdf) | No |\n| 2015 | [A deep neural network for modeling music](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FXiaoqing_Zheng3\u002Fpublication\u002F275347034_A_Deep_Neural_Network_for_Modeling_Music\u002Flinks\u002F5539d2060cf2239f4e7dad0d\u002FA-Deep-Neural-Network-for-Modeling-Music.pdf) | No |\n| 2016 | [An efficient approach for segmentation, feature extraction and classification of audio signals](http:\u002F\u002Ffile.scirp.org\u002Fpdf\u002FCS_2016042615054817.pdf) | No |\n| 2016 | [Text-based LSTM networks for automatic music composition](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F0B1OooSxEtl0FcG9MYnY2Ylh5c0U\u002Fview) | No |\n| 2016 | [Towards playlist generation algorithms using RNNs trained on within-track transitions](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1606.02096.pdf) | No |\n| 2016 | [Automatic tagging using deep convolutional neural networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1606.00298.pdf) | No |\n| 2016 | [Automatic chord estimation on seventhsbass chord vocabulary using deep neural network](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7471677\u002F) | No |\n| 2016 | [DeepBach: A steerable model for Bach chorales generation](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1612.01010.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FGhadjeres\u002FDeepBach) |\n| 2016 | [Bayesian meter tracking on learned signal representations](http:\u002F\u002Fwww.rhythmos.org\u002FMMILab-Andre_files\u002FISMIR2016_CNNDBNbeats_camready.pdf) | No |\n| 2016 | [Deep learning for music](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1606.04930.pdf) | No |\n| 2016 | [Learning temporal features using a deep neural network and its application to music genre classification](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FIl_Young_Jeong\u002Fpublication\u002F305683876_Learning_temporal_features_using_a_deep_neural_network_and_its_application_to_music_genre_classification\u002Flinks\u002F5799a27c08aec89db7bb9f92.pdf) | No |\n| 2016 | [On the potential of simple framewise approaches to piano transcription](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1612.05153.pdf) | No |\n| 2016 | [Feature learning for chord recognition: The deep chroma extractor](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1612.05065.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Ffdlm\u002Fchordrec\u002Ftree\u002Fmaster\u002Fexperiments\u002Fismir2016) |\n| 2016 | [A fully convolutional deep auditory model for musical chord recognition](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FFilip_Korzeniowski\u002Fpublication\u002F305590295_A_Fully_Convolutional_Deep_Auditory_Model_for_Musical_Chord_Recognition\u002Flinks\u002F579486ba08aed51475cc6958\u002FA-Fully-Convolutional-Deep-Auditory-Model-for-Musical-Chord-Recognition.pdf?_iepl%5BhomeFeedViewId%5D=HTzFFmKPia2YminQ4psHT5at&_iepl%5Bcontexts%5D%5B0%5D=pcfhf&_iepl%5BinteractionType%5D=publicationDownload&origin=publication_detail&ev=pub_int_prw_xdl&msrp=Dz_6LKHzYcPyP-LmgZPF-m63ayZ6k0entFEntooiu_e32zfETNQXKPQSTFOI87NONIIQuUQdnUtwORdomTXfteTrb09KiAIdDtBJnw_02P6JeRr5zu2eyaCG.2Uxsi_eENxtbYL39lvorIK8LofRYhkgpUHzpzmVzkIEiyHc0wUY87rEa4PH1qbXi4k4RyagHUsA2IsZtewnprglORjx2v9Cwbk9ZfQ.cd67BaqtHul_hE6SX6vUFKuldz81aH6dWq-cYMkq5vQKCHcvB8l9zgeM694Efb_r2wBB5GT9idt3OLeME0UxVHI6ROxamgK3LMNlSw.JtZXAo9HhR9t-8Wl3gxJgnoM4--rtmDEUDbXSWezbFyU-CoB_nyfxbRQ4kdoN4-5aJ3Tgx4YHdikicqAhc_cezB2ZntjxkB4rEDx1A) | No |\n| 2016 | [A deep bidirectional long short-term memory based multi-scale approach for music dynamic emotion prediction](http:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F7471734\u002F) | No |\n| 2016 | [Event localization in music auto-tagging](http:\u002F\u002Fmac.citi.sinica.edu.tw\u002F~yang\u002Fpub\u002Fliu16mm.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fciaua\u002Fclip2frame) |\n| 2016 | [Deep convolutional networks on the pitch spiral for musical instrument recognition](https:\u002F\u002Fgithub.com\u002Flostanlen\u002Fismir2016\u002Fblob\u002Fmaster\u002Fpaper\u002Flostanlen_ismir2016.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Flostanlen\u002Fismir2016) |\n| 2016 | [SampleRNN: An unconditional end-to-end neural audio generation model](https:\u002F\u002Fopenreview.net\u002Fpdf?id=SkxKPDv5xl) | [GitHub](https:\u002F\u002Fgithub.com\u002Fsoroushmehr\u002FsampleRNN_ICLR2017) |\n| 2016 | [Robust audio event recognition with 1-max pooling convolutional neural networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1604.06338.pdf) | No |\n| 2016 | [Experimenting with musically motivated convolutional neural networks](http:\u002F\u002Fjordipons.me\u002Fmedia\u002FCBMI16.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fjordipons\u002F) |\n| 2016 | [Singing voice melody transcription using deep neural networks](https:\u002F\u002Fwp.nyu.edu\u002Fismir2016\u002Fwp-content\u002Fuploads\u002Fsites\u002F2294\u002F2016\u002F07\u002F163_Paper.pdf) | No |\n| 2016 | [Singing voice separation using deep neural networks and F0 estimation](http:\u002F\u002Fwww.music-ir.org\u002Fmirex\u002Fabstracts\u002F2016\u002FRSGP1.pdf) | [Website](http:\u002F\u002Fcvssp.org\u002Fprojects\u002Fmaruss\u002Fmirex2016\u002F) |\n| 2016 | [Learning to pinpoint singing voice from weakly labeled examples](http:\u002F\u002Fwww.ofai.at\u002F~jan.schlueter\u002Fpubs\u002F2016_ismir.pdf) | No |\n| 2016 | [Analysis of time-frequency representations for musical onset detection with convolutional neural network](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7733228\u002F) | No |\n| 2016 | [Note onset detection in musical signals via neural-network-based multi-ODF fusion](https:\u002F\u002Fwww.degruyter.com\u002Fdownloadpdf\u002Fj\u002Famcs.2016.26.issue-1\u002Famcs-2016-0014\u002Famcs-2016-0014.pdf) | No |\n| 2016 | [Music transcription modelling and composition using deep learning](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F0B1OooSxEtl0FcTBiOGdvSTBmWnc\u002Fview) | [GitHub](https:\u002F\u002Fgithub.com\u002FIraKorshunova\u002Ffolk-rnn) |\n| 2016 | [Convolutional neural network for robust pitch determination](http:\u002F\u002Fwww.mirlab.org\u002Fconference_papers\u002FInternational_Conference\u002FICASSP%202016\u002Fpdfs\u002F0000579.pdf) | No |\n| 2016 | [Deep convolutional neural networks and data augmentation for acoustic event detection](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1604.07160.pdf) | [Website](https:\u002F\u002Fbitbucket.org\u002Fnaoya1\u002Faenet_release) |\n| 2017 | [Gabor frames and deep scattering networks in audio processing](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.08818.pdf) | No |\n| 2017 | [Vision-based detection of acoustic timed events: A case study on clarinet note onsets](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fbazzica2017clarinet.pdf) | No |\n| 2017 | [Deep learning techniques for music generation - A survey](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.01620.pdf) | No |\n| 2017 | [JamBot: Music theory aware chord based generation of polyphonic music with LSTMs](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1711.07682.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fbrunnergino\u002FJamBot) |\n| 2017 | [XFlow: 1D \u003C-> 2D cross-modal deep neural networks for audiovisual classification](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.00572.pdf) | No |\n| 2017 | [Machine listening intelligence](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fcella2017mli.pdf) | No |\n| 2017 | [Monoaural audio source separation using deep convolutional neural networks](http:\u002F\u002Fmtg.upf.edu\u002Fsystem\u002Ffiles\u002Fpublications\u002Fmonoaural-audio-source_0.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FMTG\u002FDeepConvSep) |\n| 2017 | [Deep multimodal network for multi-label classification](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8019322\u002F) | No |\n| 2017 | [A tutorial on deep learning for music information retrieval](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.04396.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi\u002Fdl4mir) |\n| 2017 | [A comparison on audio signal preprocessing methods for deep neural networks on music tagging](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.01922.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi\u002Ftransfer_learning_music) |\n| 2017 | [Transfer learning for music classification and regression tasks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.09179v3.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi\u002Ftransfer_learning_music) |\n| 2017 | [Convolutional recurrent neural networks for music classification](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7952585\u002F) | [GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi\u002Ficassp_2017) |\n| 2017 | [An evaluation of convolutional neural networks for music classification using spectrograms](http:\u002F\u002Fwww.inf.ufpr.br\u002Flesoliveira\u002Fdownload\u002FASOC2017.pdf) | No |\n| 2017 | [Large vocabulary automatic chord estimation using deep neural nets: Design framework, system variations and limitations](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.07153.pdf) | No |\n| 2017 | [Basic filters for convolutional neural networks: Training or design?](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.02291.pdf) | No |\n| 2017 | [Ensemble Of Deep Neural Networks For Acoustic Scene Classification](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1708.05826.pdf) | No |\n| 2017 | [Robust downbeat tracking using an ensemble of convolutional networks](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7728057\u002F) | No |\n| 2017 | [Music signal processing using vector product neural networks](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Ffan2017vector.pdf) | No |\n| 2017 | [Transforming musical signals through a genre classifying convolutional neural network](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fgeng2017genre.pdf) | No |\n| 2017 | [Audio to score matching by combining phonetic and duration information](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.03547.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fronggong\u002FjingjuSingingPhraseMatching\u002Ftree\u002Fv0.1.0) |\n| 2017 | [Interactive music generation with positional constraints using anticipation-RNNs](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.06404.pdf) | No |\n| 2017 | [Deep rank-based transposition-invariant distances on musical sequences](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.00740.pdf) | No |\n| 2017 | [GLSR-VAE: Geodesic latent space regularization for variational autoencoder architectures](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.04588.pdf) | No |\n| 2017 | [Deep convolutional neural networks for predominant instrument recognition in polyphonic music](http:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3068697) | No |\n| 2017 | [CNN architectures for large-scale audio classification](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1609.09430v2.pdf) | No |\n| 2017 | [DeepSheet: A sheet music generator based on deep learning](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8026272\u002F) | No |\n| 2017 | [Talking Drums: Generating drum grooves with neural networks](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fhutchings2017drums.pdf) | No |\n| 2017 | [Singing voice separation with deep U-Net convolutional networks](https:\u002F\u002Fismir2017.smcnus.org\u002Fwp-content\u002Fuploads\u002F2017\u002F10\u002F171_Paper.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FXiao-Ming\u002FUNet-VocalSeparation-Chainer) |\n| 2017 | [Music emotion recognition via end-to-end multimodal neural networks](http:\u002F\u002Fceur-ws.org\u002FVol-1905\u002Frecsys2017_poster18.pdf) | No |\n| 2017 | [Chord label personalization through deep learning of integrated harmonic interval-based representations](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fkoops2017pers.pdf) | No |\n| 2017 | [End-to-end musical key estimation using a convolutional neural network](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.02921.pdf) | No |\n| 2017 | [MediaEval 2017 AcousticBrainz genre task: Multilayer perceptron approach](http:\u002F\u002Fwww.cp.jku.at\u002Fresearch\u002Fpapers\u002FKoutini_2017_mediaeval-acousticbrainz.pdf) | No |\n| 2017 | [Classification-based singing melody extraction using deep convolutional neural networks](https:\u002F\u002Fwww.preprints.org\u002Fmanuscript\u002F201711.0027\u002Fv1) | No |\n| 2017 | [Multi-level and multi-scale feature aggregation using pre-trained convolutional neural networks for music auto-tagging](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.01793v2.pdf) | No |\n| 2017 | [Multi-level and multi-scale feature aggregation using sample-level deep convolutional neural networks for music classification](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.06810.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fjongpillee\u002FmusicTagging_MSD) |\n| 2017 | [Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.01789v2.pdf) | No |\n| 2017 | [A SeqGAN for Polyphonic Music Generation](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1710.11418.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FL0SG\u002Fseqgan-music) |\n| 2017 | [Harmonic and percussive source separation using a convolutional auto encoder](http:\u002F\u002Fwww.eurasip.org\u002FProceedings\u002FEusipco\u002FEusipco2017\u002Fpapers\u002F1570346835.pdf) | No |\n| 2017 | [Stacked convolutional and recurrent neural networks for music emotion recognition](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.02292.pdf) | No |\n| 2017 | [A deep learning approach to source separation and remixing of hiphop music](https:\u002F\u002Frepositori.upf.edu\u002Fbitstream\u002Fhandle\u002F10230\u002F32919\u002FMartel_2017.pdf?sequence=1&isAllowed=y) | No |\n| 2017 | [Music Genre Classification Using Masked Conditional Neural Networks](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007%2F978-3-319-70096-0_49) | No |\n| 2017 | [Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1711.01437.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FJs-Mim\u002Fmss_pytorch) |\n| 2017 | [Generating data to train convolutional neural networks for classical music source separation](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FMarius_Miron\u002Fpublication\u002F318322107_Generating_data_to_train_convolutional_neural_networks_for_classical_music_source_separation\u002Flinks\u002F59637cc3458515a3575b93c6\u002FGenerating-data-to-train-convolutional-neural-networks-for-classical-music-source-separation.pdf?_iepl%5BhomeFeedViewId%5D=WchoMnlUL1Hk9hBLVTeR8Amh&_iepl%5Bcontexts%5D%5B0%5D=pcfhf&_iepl%5BinteractionType%5D=publicationDownload&origin=publication_detail&ev=pub_int_prw_xdl&msrp=p3lQ8M4uZlb4TF5Hv9a2U3P2y4wW7ant5KWj4E5-OcD1Mg53p1ykTKHMG9_zVTB9n6mI8fvZOCL2Xhpru186pCEY-2ZxiYR-CB8_QvwHc1kUG-QE4SHdProR.LoJb2BDOiiQth3iR9xgZUxxCWEJgtTBF4whFrFa01OD49-3YYRxA0WQVN--zhtQU_7C2Pt0rKdwoFxT1pfxFvnKXSXmy2eT1Jpz-pw.U1QLoFO_Uc6aQVr2Nm2FcAi6BqAUfngH2Or5__6wegbCgVvTYoIGt22tmCkYbGTOQ_4PxBgt1LrvsFQiL0oMyogP8Yk8myTj0gs9jw.fGpkufGqAI4R2v8Hfe0ThcXL7M7yN2PuAlx974BGVn50SdUWvNhhIPWBD-zWTn8NKtVJx3XrjKXFrMgi9Cx7qGrNP8tBWpha6Srf6g) | [GitHub](https:\u002F\u002Fgithub.com\u002FMTG\u002FDeepConvSep) |\n| 2017 | [Monaural score-informed source separation for classical music using convolutional neural networks](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FMarius_Miron\u002Fpublication\u002F318637038_Monaural_score-informed_source_separation_for_classical_music_using_convolutional_neural_networks\u002Flinks\u002F597327c6458515e26dfdb007\u002FMonaural-score-informed-source-separation-for-classical-music-using-convolutional-neural-networks.pdf?_iepl%5BhomeFeedViewId%5D=WchoMnlUL1Hk9hBLVTeR8Amh&_iepl%5Bcontexts%5D%5B0%5D=pcfhf&_iepl%5BinteractionType%5D=publicationDownload&origin=publication_detail&ev=pub_int_prw_xdl&msrp=Hp6dDqMepEiRZ5E6WkreaqyjFkFkwMxPFoJvr14etVJsoKZBc5qb99fBnJjVUZrRHLFRhaXvNY9k1sMvYPOouuGbQP0YhEGm28zLw_55Zewu86WGnHck1Tqi.93HH2WqXfTedn6IaZRjjhQGYZVDHBz1X6nr4ABBgMAVv584gvGN3sW5IyBAY-4MBWf5DJFPBGm8zsaC2dKz8G-odZPfosWoXY0afAQ.KoCP2mO9l31lCER0oMZMZBrbuRGvb6ZzeBwHb88pL8AhMfJk03Hj1eLrohQIjPDETBj4hhqb0gniDGJgtZ9GnW64ZNjh9GbQDrIl5A.egNQTyC7t8P26zCQWrbEhf51Pxy2JRBZoTkH6SpRHHhRhFl1_AT_AT481lMcFI34-JbeRq-5oTQR7DpvAuw7iUIivd78ltuxpI9syg) | [GitHub](https:\u002F\u002Fgithub.com\u002FMTG\u002FDeepConvSep) |\n| 2017 | [Multi-label music genre classification from audio, text, and images using deep features](https:\u002F\u002Fismir2017.smcnus.org\u002Fwp-content\u002Fuploads\u002F2017\u002F10\u002F126_Paper.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fsergiooramas\u002Ftartarus) |\n| 2017 | [A deep multimodal approach for cold-start music recommendation](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.09739.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fsergiooramas\u002Ftartarus) |\n| 2017 | [Melody extraction and detection through LSTM-RNN with harmonic sum loss](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7952660\u002F) | No |\n| 2017 | [Representation learning of music using artist labels](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1710.06648.pdf) | No |\n| 2017 | [Toward inverse control of physics-based sound synthesis](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fpfalz2017synthesis.pdf) | [Website](https:\u002F\u002Fwww.cct.lsu.edu\u002F~apfalz\u002Finverse_control.html) |\n| 2017 | [DNN and CNN with weighted and multi-task loss functions for audio event detection](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1708.03211.pdf) | No |\n| 2017 | [Score-informed syllable segmentation for a cappella singing voice with convolutional neural networks](https:\u002F\u002Fismir2017.smcnus.org\u002Fwp-content\u002Fuploads\u002F2017\u002F10\u002F46_Paper.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fronggong\u002FjingjuSyllabicSegmentaion\u002Ftree\u002Fv0.1.0) |\n| 2017 | [End-to-end learning for music audio tagging at scale](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1711.02520.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fjordipons\u002Fmusic-audio-tagging-at-scale-models) |\n| 2017 | [Designing efficient architectures for modeling temporal features with convolutional neural networks](http:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F7952601\u002F) | [GitHub](https:\u002F\u002Fgithub.com\u002Fjordipons\u002FICASSP2017) |\n| 2017 | [Timbre analysis of music audio signals with convolutional neural networks](https:\u002F\u002Fgithub.com\u002Fronggong\u002FEUSIPCO2017) | [GitHub](https:\u002F\u002Fgithub.com\u002Fjordipons\u002FEUSIPCO2017) |\n| 2017 | [The MUSDB18 corpus for music separation](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.1117372) | [GitHub](https:\u002F\u002Fgithub.com\u002Fsigsep\u002Fwebsite) |\n| 2017 | [Deep learning and intelligent audio mixing](http:\u002F\u002Fwww.semanticaudio.co.uk\u002Fwp-content\u002Fuploads\u002F2017\u002F09\u002FWIMP2017_Martinez-RamirezReiss.pdf) | No |\n| 2017 | [Deep learning for event detection, sequence labelling and similarity estimation in music signals](http:\u002F\u002Fofai.at\u002F~jan.schlueter\u002Fpubs\u002Fphd\u002Fphd.pdf) | No |\n| 2017 | [Music feature maps with convolutional neural networks for music genre classification](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FThomas_Pellegrini\u002Fpublication\u002F319326354_Music_Feature_Maps_with_Convolutional_Neural_Networks_for_Music_Genre_Classification\u002Flinks\u002F59ba5ae3458515bb9c4c6724\u002FMusic-Feature-Maps-with-Convolutional-Neural-Networks-for-Music-Genre-Classification.pdf?origin=publication_detail&ev=pub_int_prw_xdl&msrp=wzXuHZAa5zAnqEmErYyZwIRr2H0q01LnNEd4Wd7A15CQfdVLwdy98pmE-AdnrDvoc3-bVENSFrHt0yhaOiE2mQrYllVS9CJZOk-c9R0j_R1rbgcZugS6RtQ_.AUjPuJSF5P_DMngf-woH7W-7jdnQlbNQziR4_h6NnCHfR_zGcEa8vOyyOz5gx5nc4azqKTPQ5ZgGGLUxkLj1qCQLEQ5ThkhGlWHLyA.s6MBZE20-EO_RjRGCOCV4wk0WSFdN56Aloiraxz9hKCbJwRM2Et27RHVUA8jj9H8qvXIB6f7zSIrQgjXGrL2yCpyQlLffuf57rzSwg.KMMXbZrHsihV8DJM53xkHAWf3VebCJESi4KU4btNv9nQsyK2KnkhSQaTILKv0DSZY3c70a61LzywCBuoHtIhVOFhW5hVZN2n5O9uKQ) | No |\n| 2017 | [Automatic drum transcription for polyphonic recordings using soft attention mechanisms and convolutional neural networks](https:\u002F\u002Fcarlsouthall.files.wordpress.com\u002F2017\u002F12\u002Fismir2017adt.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FCarlSouthall\u002FADTLib) |\n| 2017 | [Adversarial semi-supervised audio source separation applied to singing voice extraction](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1711.00048.pdf) | No |\n| 2017 | [Taking the models back to music practice: Evaluating generative transcription models built using deep learning](http:\u002F\u002Fjcms.org.uk\u002Fissues\u002FVol2Issue1\u002Ftaking-models-back-to-music-practice\u002FTaking%20the%20Models%20back%20to%20Music%20Practice:%20Evaluating%20Generative%20Transcription%20Models%20built%20using%20Deep%20Learning.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FIraKorshunova\u002Ffolk-rnn) |\n| 2017 | [Generating nontrivial melodies for music as a service](https:\u002F\u002Fismir2017.smcnus.org\u002Fwp-content\u002Fuploads\u002F2017\u002F10\u002F178_Paper.pdf) | No |\n| 2017 | [Invariances and data augmentation for supervised music transcription](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1711.04845.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fjthickstun\u002Fthickstun2018invariances\u002F) |\n| 2017 | [Lyrics-based music genre classification using a hierarchical attention network](https:\u002F\u002Fismir2017.smcnus.org\u002Fwp-content\u002Fuploads\u002F2017\u002F10\u002F43_Paper.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FalexTsaptsinos\u002FlyricsHAN) |\n| 2017 | [A hybrid DSP\u002Fdeep learning approach to real-time full-band speech enhancement](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.08243.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fxiph\u002Frnnoise\u002F) |\n| 2017 | [Convolutional methods for music analysis](http:\u002F\u002Fvbn.aau.dk\u002Ffiles\u002F260308151\u002FPHD_Gissel_Velarde_E_pdf.pdf) | No |\n| 2017 | [Extending temporal feature integration for semantic audio analysis](http:\u002F\u002Fwww.aes.org\u002Fe-lib\u002Fbrowse.cfm?elib=18682) | No |\n| 2017 | [Recognition and retrieval of sound events using sparse coding convolutional neural network](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8019552\u002F) | No |\n| 2017 | [A two-stage approach to note-level transcription of a specific piano](http:\u002F\u002Fwww.mdpi.com\u002F2076-3417\u002F7\u002F9\u002F901\u002Fhtm) | No |\n| 2017 | [Reducing model complexity for DNN based large-scale audio classification](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1711.00229.pdf) | No |\n| 2017 | [Audio spectrogram representations for processing with convolutional neural networks](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fwyse2017spect.pdf) | [Website](http:\u002F\u002Flonce.org\u002Fresearch\u002FaudioST\u002F) |\n| 2017 | [Unsupervised feature learning based on deep models for environmental audio tagging](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1607.03681.pdf) | No |\n| 2017 | [Attention and localization based on a deep convolutional recurrent model for weakly supervised audio tagging](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.06052.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FyongxuUSTC\u002Fatt_loc_cgrnn) |\n| 2017 | [Surrey-CVSSP system for DCASE2017 challenge task4](https:\u002F\u002Fwww.cs.tut.fi\u002Fsgn\u002Farg\u002Fdcase2017\u002Fdocuments\u002Fchallenge_technical_reports\u002FDCASE2017_Xu_146.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FyongxuUSTC\u002Fdcase2017_task4_cvssp) |\n| 2017 | [A study on LSTM networks for polyphonic music sequence modelling](https:\u002F\u002Fqmro.qmul.ac.uk\u002Fxmlui\u002Fhandle\u002F123456789\u002F24946) | [Website](http:\u002F\u002Fwww.eecs.qmul.ac.uk\u002F~ay304\u002Fcode\u002Fismir17) |\n| 2018 | [MuseGAN: Multi-track sequential generative adversarial networks for symbolic music generation and accompaniment](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.06298.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fsalu133445\u002Fmusegan) |\n| 2018 | [Music transformer: Generating music with long-term structure](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1809.04281.pdf) | No |\n| 2018 | [Music theory inspired policy gradient method for piano music transcription](https:\u002F\u002Fnips2018creativity.github.io\u002Fdoc\u002Fmusic_theory_inspired_policy_gradient.pdf) | No |\n| 2019 | [Enabling factorized piano music modeling and generation with the MAESTRO dataset](https:\u002F\u002Farxiv.org\u002Fabs\u002F1810.12247) | [GitHub](https:\u002F\u002Fgithub.com\u002Fmagenta\u002Fmagenta\u002Ftree\u002Fmaster\u002Fmagenta\u002Fmodels\u002Fonsets_frames_transcription) |\n| 2019 | [Generating Long Sequences with Sparse Transformers](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1904.10509.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fsparse_attention) |\n| 2021 | [DadaGP: a Dataset of Tokenized GuitarPro Songs for Sequence Models](https:\u002F\u002Farchives.ismir.net\u002Fismir2021\u002Fpaper\u002F000076.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fdada-bots\u002FdadaGP) |\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## DL4M details\n\nA human-readable table summarized version if displayed in the file [dl4m.tsv](dl4m.tsv). All details for each article are stored in the corresponding bib entry in [dl4m.bib](dl4m.bib). Each entry has the regular bib field:\n\n- `author`\n- `year`\n- `title`\n- `journal` or `booktitle`\n\nEach entry in [dl4m.bib](dl4m.bib) also displays additional information:\n\n- `link` - HTML link to the PDF file\n- `code` - Link to the source code if available\n- `archi` - Neural network architecture\n- `layer` - Number of layers\n- `task` - The proposed tasks studied in the article\n- `dataset` - The names of the dataset used\n- `dataaugmentation` - The type of data augmentation technique used\n- `time` - The computation time\n- `hardware` - The hardware used\n- `note` - Additional notes and information\n- `repro` - Indication to what extent the experiments are reproducible\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## Code without articles\n\n- [Audio Classifier in Keras using Convolutional Neural Network](https:\u002F\u002Fgithub.com\u002Fdrscotthawley\u002Faudio-classifier-keras-cnn)\n- [Deep learning driven jazz generation using Keras & Theano](https:\u002F\u002Fgithub.com\u002Fjisungk\u002Fdeepjazz)\n- [End-to-end learning for music audio tagging at scale](https:\u002F\u002Fgithub.com\u002Fjordipons\u002Fmusic-audio-tagging-at-scale-models)\n- [Music Genre classification on GTZAN dataset using CNNs](https:\u002F\u002Fgithub.com\u002FHguimaraes\u002Fgtzan.keras)\n- [Pitch Estimation of Choir Music using Deep Learning Strategies: from Solo to Unison Recordings](https:\u002F\u002Fgithub.com\u002Fhelenacuesta\u002Fchoir-pitch-estimation)\n- [Music Genre Classification with LSTMs](https:\u002F\u002Fgithub.com\u002Fruohoruotsi\u002FLSTM-Music-Genre-Classification)\n- [CNN based Music Emotion Classification using TensorFlow](https:\u002F\u002Fgithub.com\u002Frickiepark\u002Fcnn_mer)\n- [Separating singing voice from music based on deep neural networks in Tensorflow](https:\u002F\u002Fgithub.com\u002Fandabi\u002Fmusic-source-separation)\n- [Music tag classification model using CRNN](https:\u002F\u002Fgithub.com\u002Fkristijanbartol\u002FDeep-Music-Tagger)\n- [Finding the genre of a song with Deep Learning](https:\u002F\u002Fgithub.com\u002Fdespoisj\u002FDeepAudioClassification)\n- [Composing music using neural nets](https:\u002F\u002Fgithub.com\u002Ffephsun\u002Fneuralnetmusic)\n- [Performance-RNN-PyTorch](https:\u002F\u002Fgithub.com\u002Fdjosix\u002FPerformance-RNN-PyTorch)\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## Statistics and visualisations\n\n- 167 papers referenced. See the details in [dl4m.bib](dl4m.bib).\nThere are more papers from 2017 than any other years combined.\nNumber of articles per year:\n![Number of articles per year](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_4b3e5a139a32.png)\n- If you are applying DL to music, there are [364 other researchers](authors.md) in your field.\n- 34 tasks investigated. See the list of [tasks](tasks.md).\nTasks pie chart:\n![Tasks pie chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_b37647cd735a.png)\n- 55 datasets used. See the list of [datasets](datasets.md).\nDatasets pie chart:\n![Datasets pie chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_1feb58db0c7b.png)\n- 30 architectures used. See the list of [architectures](architectures.md).\nArchitectures pie chart:\n![Architectures pie chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_39713cf04823.png)\n- 9 frameworks used. See the list of [frameworks](frameworks.md).\nFrameworks pie chart:\n![Frameworks pie chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_aff3848209e7.png)\n- Only 47 articles (28%) provide their source code.\nRepeatability is the key to good science, so check out the [list of useful resources on reproducibility for MIR and ML](reproducibility.md).\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## Advices for reviewers of dl4m articles\n\nPlease refer to the [advice_review.md](advice_review.md) file.\n\n## How To Contribute\n\nContributions are welcome!\nPlease refer to the [CONTRIBUTING.md](CONTRIBUTING.md) file.\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## FAQ\n\n> How are the articles sorted?\n\nThe articles are first sorted by decreasing year (to keep up with the latest news) and then alphabetically by the main author's family name.\n\n> Why are preprint from arXiv included in the list?\n\nI want to have exhaustive research and the latest news on DL4M. However, one should take care of the information provided in the articles currently in review. If possible you should wait for the final accepted and peer-reviewed version before citing an arXiv paper. I regularly update the arXiv links to the corresponding published papers when available.\n\n> How much can I trust the results published in an article?\n\nThe list provided here does not guarantee the quality of the articles. You should either try to reproduce the experiments described or submit a request to [ReScience](https:\u002F\u002Fgithub.com\u002FReScience\u002FReScience). Use one article's conclusion at your own risks.\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## Acronyms used\n\nA list of useful acronyms used in deep learning and music is stored in [acronyms.md](acronyms.md).\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## Sources\n\nThe list of conferences, journals and aggregators used to gather the proposed materials is stored in [sources.md](sources.md).\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## Contributors\n\n- [Yann Bayle](http:\u002F\u002Fyannbayle.fr\u002Fenglish\u002Findex.php) ([GitHub](https:\u002F\u002Fgithub.com\u002Fybayle)) - Instigator and principal maintainer\n- Vincent Lostanlen ([GitHub](https:\u002F\u002Fgithub.com\u002Flostanlen))\n- [Keunwoo Choi](https:\u002F\u002Fkeunwoochoi.wordpress.com\u002F) ([GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi))\n- [Bob L. Sturm](http:\u002F\u002Fwww.eecs.qmul.ac.uk\u002F~sturm\u002F) ([GitHub](https:\u002F\u002Fgithub.com\u002Fboblsturm))\n- [Stefan Balke](https:\u002F\u002Fwww.audiolabs-erlangen.de\u002Ffau\u002Fassistant\u002Fbalke) ([GitHub](https:\u002F\u002Fgithub.com\u002Fstefan-balke))\n- [Jordi Pons](http:\u002F\u002Fwww.jordipons.me\u002F) ([GitHub](https:\u002F\u002Fgithub.com\u002Fjordipons))\n- Mirza Zulfan ([GitHub](https:\u002F\u002Fgithub.com\u002Fmirzazulfan)) for the logo\n- [Devin Walters](https:\u002F\u002Fgithub.com\u002Fdevn)\n- https:\u002F\u002Fgithub.com\u002FLegendJ\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## Other useful related lists and resources\n\n#### Audio\n\n- [DL4MIR tutorial with keras](https:\u002F\u002Fgithub.com\u002Ftuwien-musicir\u002FDL_MIR_Tutorial) - Tutorial for Deep Learning on Music Information Retrieval by [Thomas Lidy](http:\u002F\u002Fifs.tuwien.ac.at\u002F~lidy\u002F)\n- [Video talk from Ron Weiss](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=sI_8EA0_ha8) - Ron Weiss (Google) Talk on Training neural network acoustic models on waveforms\n- [Slides on DL4M](http:\u002F\u002Fwww.jordipons.me\u002Fmedia\u002FDL4Music_Pons.pdf) - A personal (re)view of the state-of-the-art by [Jordi Pons](http:\u002F\u002Fwww.jordipons.me\u002F)\n- [DL4MIR tutorial](https:\u002F\u002Fgithub.com\u002Fmarl\u002Fdl4mir-tutorial) - Python tutorials for learning to solve MIR tasks with DL\n- [Awesome Python Scientific Audio](https:\u002F\u002Fgithub.com\u002Ffaroit\u002Fawesome-python-scientific-audio) - Python resources for Audio and Machine Learning\n- [ISMIR resources](http:\u002F\u002Fismir.net\u002Fresources.php) - Community maintained list\n- [ISMIR Google group](https:\u002F\u002Fgroups.google.com\u002Fa\u002Fismir.net\u002Fforum\u002F#!forum\u002Fcommunity) - Daily dose of general MIR\n- [Awesome Python](https:\u002F\u002Fgithub.com\u002Fvinta\u002Fawesome-python#audio) - Audio section of Python resources\n- [Awesome Web Audio](https:\u002F\u002Fgithub.com\u002Fnotthetup\u002Fawesome-webaudio) - WebAudio packages and resources\n- [Awesome Music](https:\u002F\u002Fgithub.com\u002Fciconia\u002Fawesome-music) - Music softwares\n- [Awesome Music Production](https:\u002F\u002Fgithub.com\u002Fadius\u002Fawesome-music-production) - Music creation\n- [The Asimov Institute](http:\u002F\u002Fwww.asimovinstitute.org\u002Fanalyzing-deep-learning-tools-music\u002F) - 6 deep learning tools for music generation\n- [DLM Google group](https:\u002F\u002Fgroups.google.com\u002Fforum\u002F#!forum\u002Ficdlm) - Deep Learning in Music group\n- [MIR community on Slack](https:\u002F\u002Fslackpass.io\u002Fmircommunity) - Link to subscribe to the MIR community's Slack\n- [Unclassified list of MIR-related links](http:\u002F\u002Fwww.music.mcgill.ca\u002F~cmckay\u002Flinks_academic.html) - [Cory McKay](http:\u002F\u002Fwww.music.mcgill.ca\u002F~cmckay\u002F)'s list of various links on DL, MIR, ...\n- [MIRDL](http:\u002F\u002Fjordipons.me\u002Fwiki\u002Findex.php\u002FMIRDL) - Unmaintained list of DL articles for MIR from [Jordi Pons](http:\u002F\u002Fwww.jordipons.me\u002F)\n- [WWW 2018 Challenge](https:\u002F\u002Fwww.crowdai.org\u002Fchallenges\u002Fwww-2018-challenge-learning-to-recognize-musical-genre) - Learning to Recognize Musical Genre on the [FMA](https:\u002F\u002Fgithub.com\u002Fmdeff\u002Ffma) dataset\n- [Music generation with DL](https:\u002F\u002Fgithub.com\u002Fumbrellabeach\u002Fmusic-generation-with-DL) - List of resources on music generation with deep learning\n- [Auditory Scene Analysis](https:\u002F\u002Fmitpress.mit.edu\u002Fbooks\u002Fauditory-scene-analysis) - Book about the perceptual organization of sound by [Albert Bregman](https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAlbert_Bregman), the \"father of [Auditory Scene Analysis](https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAuditory_scene_analysis)\".\n  - [Demonstrations of Auditory Scene Analysis](http:\u002F\u002Fwebpages.mcgill.ca\u002Fstaff\u002FGroup2\u002Fabregm1\u002Fweb\u002Fdownloadstoc.htm) - Audio demonstrations, which illustrate examples of auditory perceptual organization.\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n#### Music datasets\n\n- [AudioContentAnalysis nearly exhaustive list of music-related datasets](http:\u002F\u002Fwww.audiocontentanalysis.org\u002Fdata-sets\u002F)\n- [Teaching MIR](https:\u002F\u002Fteachingmir.wikispaces.com\u002FDatasets)\n- [Wikipedia's list of datasets for machine learning research](https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FList_of_datasets_for_machine_learning_research#cite_ref-215)\n- [Datasets for deep learning](http:\u002F\u002Fdeeplearning.net\u002Fdatasets\u002F)\n- [Awesome public datasets](https:\u002F\u002Fgithub.com\u002Fcaesar0301\u002Fawesome-public-datasets)\n- [Awesome music listening](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-music-listening)\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n#### Deep learning\n\n- [DLPaper2Code: Auto-generation of Code from Deep Learning Research Papers](https:\u002F\u002Farxiv.org\u002Fabs\u002F1711.03543) -\n- [Model Convertors](https:\u002F\u002Fgithub.com\u002Fysh329\u002Fdeep-learning-model-convertor) - Convertors for DL frameworks and backend\n- [Deep architecture genealogy](https:\u002F\u002Fgithub.com\u002Fhunkim\u002Fdeep_architecture_genealogy) - Genealogy of DL architectures\n- [Deep Learning as an Engineer](http:\u002F\u002Fwww.univie.ac.at\u002Fnuhag-php\u002Fdateien\u002Ftalks\u002F3358_schlueter.pdf) - Slides from Jan Schlüter\n- [Awesome Deep Learning](https:\u002F\u002Fgithub.com\u002FChristosChristofidis\u002Fawesome-deep-learning) - General deep learning resources\n- [Awesome Deep Learning Resources](https:\u002F\u002Fgithub.com\u002Fendymecy\u002Fawesome-deeplearning-resources) - Papers regarding deep learning and deep reinforcement learning\n- [Awesome RNNs](https:\u002F\u002Fgithub.com\u002Fkjw0612\u002Fawesome-rnn) - RNNs code, theory and applications\n- [Cheatsheets AI](https:\u002F\u002Fgithub.com\u002Fkailashahirwar\u002Fcheatsheets-ai) - Cheat Sheets for Keras, neural networks, scikit-learn,...\n- [DL PaperNotes](https:\u002F\u002Fgithub.com\u002Fdennybritz\u002Fdeeplearning-papernotes) - Summaries and notes on general deep learning research papers\n- General [![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome) lists\n- [Echo State Network](http:\u002F\u002Fminds.jacobs-university.de\u002Fsites\u002Fdefault\u002Ffiles\u002Fuploads\u002Fpapers\u002FPracticalESN.pdf)\n- [DL in NLP](http:\u002F\u002Fruder.io\u002Fdeep-learning-nlp-best-practices\u002Findex.html#introduction) - Best practices for using neural networks by [Sebastian Ruder](http:\u002F\u002Fruder.io\u002F)\n- [CNN overview](http:\u002F\u002Fcs231n.github.io\u002Fconvolutional-networks\u002F) - Stanford Course\n- [Dilated Recurrent Neural Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1710.02224.pdf) - How to improve RNNs?\n- [Encoder-Decoder in RNNs](https:\u002F\u002Fmachinelearningmastery.com\u002Fhow-does-attention-work-in-encoder-decoder-recurrent-neural-networks\u002F?utm_content=buffer0d2a7&utm_medium=social&utm_source=twitter.com&utm_campaign=bufferhttps:\u002F\u002Fblog.recast.ai\u002Fml-spotlight-rnn\u002F?utm_content=bufferf19d3&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer) - How Does Attention Work in Encoder-Decoder Recurrent Neural Networks\n- [On the use of DL](https:\u002F\u002Ftwitter.com\u002Frandal_olson\u002Fstatus\u002F927157485240311808\u002Fphoto\u002F1) - Misc fun around DL\n- [ML from scratch](https:\u002F\u002Fgithub.com\u002Feriklindernoren\u002FML-From-Scratch) - Python implementations of ML models and algorithms from scratch from Data Mining to DL\n- [Comparison of DL frameworks](https:\u002F\u002Fproject.inria.fr\u002Fdeeplearning\u002Ffiles\u002F2016\u002F05\u002FDLFrameworks.pdf) - Presentation describing the different existing frameworks for DL\n- [ELU > ReLU](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1511.07289.pdf) - Article describing the differences between ELU and ReLU\n- [Reinforcement Learning: An Introduction](http:\u002F\u002Fincompleteideas.net\u002Fsutton\u002Fbook\u002Fbookdraft2017nov5.pdf) - Book about reinforcement learning\n- [Estimating Optimal Learning Rate](https:\u002F\u002Ftowardsdatascience.com\u002Festimating-optimal-learning-rate-for-a-deep-neural-network-ce32f2556ce0) - Blog post on the learning rate optimisation\n- [GitHub repo for sklearn add-on for imbalanced learning](https:\u002F\u002Fgithub.com\u002Fscikit-learn-contrib\u002Fimbalanced-learn) - ML in uneven datasets\n- [Video on DL from Nando de Freitas, Scott Reed and Oriol Vinyals](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=YJnddoa8sHk) - Deep Learning: Practice and Trends (NIPS 2017 Tutorial, parts I & II)\n- [Article \"Are GANs Created Equal? A Large-Scale Study\"](https:\u002F\u002Farxiv.org\u002Fabs\u002F1711.10337) - Actually comparing DL algorithms\n- [Battle of the Deep Learning frameworks](https:\u002F\u002Ftowardsdatascience.com\u002Fbattle-of-the-deep-learning-frameworks-part-i-cff0e3841750) - DL frameworks comparison and evolution\n- [Black-box optimization](http:\u002F\u002Ftimvieira.github.io\u002Fblog\u002Fpost\u002F2018\u002F03\u002F16\u002Fblack-box-optimization\u002F) - There are other optimization algorithms than just gradient descent\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## Cited by\n\nIf you use the information contained in this repository, please let us know! This repository is cited by:\n\n- [Alexander Schindler](https:\u002F\u002Ftwitter.com\u002FSlychief\u002Fstatus\u002F915218386421997568)\n- [Meinard Müller, Christof Weiss, Stefan Balke](https:\u002F\u002Fwww.audiolabs-erlangen.de\u002Fresources\u002FMIR\u002F2017-GI-Tutorial-Musik\u002F2017_MuellerWeissBalke_GI_DeepLearningMIR.pdf)\n- [WWW 2018 Challenge: Learning to Recognize Musical Genre](https:\u002F\u002Fwww.crowdai.org\u002Fchallenges\u002Fwww-2018-challenge-learning-to-recognize-musical-genre)\n- [Awesome Deep Learning](https:\u002F\u002Fgithub.com\u002FChristosChristofidis\u002Fawesome-deep-learning)\n- [AINewsFeed](https:\u002F\u002Ftwitter.com\u002FAINewsFeed\u002Fstatus\u002F897832912351105025)\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## License\n\nYou are free to copy, modify, and distribute ***Deep Learning for Music (DL4M)*** with attribution under the terms of the MIT license. See the LICENSE file for details.\nThis project use another projects and you may refer to them for appropriate license information :\n\n- [Readme checklist](https:\u002F\u002Fgithub.com\u002Fddbeck\u002Freadme-checklist) - To build an universal Readme.\n- [Pylint](https:\u002F\u002Fwww.pylint.org\u002F) - To clean the python code.\n- [Numpy](http:\u002F\u002Fwww.numpy.org\u002F) - To manage python structure.\n- [Matplotlib](https:\u002F\u002Fmatplotlib.org\u002F) - To plot nice figures.\n- [Bibtexparser](https:\u002F\u002Fgithub.com\u002Fsciunto-org\u002Fpython-bibtexparser) - To deal with the bib entries.\n\n[Go back to top](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n","⚠️ 本仓库已停止维护。虽然信息仍然相关，但欢迎贡献以保持其更新！一个不错的起点是此处引用的文章：https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music\u002Fissues\u002F5\n\n\u003Cimg align=\"right\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_08523d25d5e6.png\">\n\n# 音乐领域的深度学习（DL4M）[![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome)\n\n由 [Yann Bayle](http:\u002F\u002Fyannbayle.fr\u002Fenglish\u002Findex.php)（[个人网站](http:\u002F\u002Fyannbayle.fr\u002Fenglish\u002Findex.php)，[GitHub](https:\u002F\u002Fgithub.com\u002Fybayle)）来自 LaBRI（[官网](http:\u002F\u002Fwww.labri.fr\u002F)，[Twitter](https:\u002F\u002Ftwitter.com\u002FlabriOfficial\u002F)）、Univ. Bordeaux（[官网](https:\u002F\u002Fwww.u-bordeaux.fr\u002F)，[Twitter](https:\u002F\u002Ftwitter.com\u002Funivbordeaux)）、CNRS（[官网](http:\u002F\u002Fwww.cnrs.fr\u002F)，[Twitter](https:\u002F\u002Ftwitter.com\u002FCNRS)）和 SCRIME（[官网](https:\u002F\u002Fscrime.u-bordeaux.fr\u002F)）。\n\n**TL;DR** 音乐领域深度学习的非详尽科学论文列表：[摘要](#dl4m-summary)（论文标题、PDF链接和代码），[详情](dl4m.tsv)（表格 - 更多信息），[详情](dl4m.bib)（参考文献格式 - 所有信息）\n\n本精选列表旨在汇总使用深度学习（Deep Learning）方法应用于音乐的科学论文、博士论文和报告。\n该列表仍在建设中，欢迎补充缺失字段或添加其他资源！请参见[如何贡献](#how-to-contribute)部分了解具体方式。\n此处提供的资源来源于我为博士论文撰写的综述文章，目前相关论文正在撰写中。\n目前已有关于深度学习在[音乐生成](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.01620.pdf)、[语音分离](https:\u002F\u002Farxiv.org\u002Fftp\u002Farxiv\u002Fpapers\u002F1708\u002F1708.07524.pdf)和[说话人识别](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FSeyed_Reza_Shahamiri\u002Fpublication\u002F319158024_Speaker_Identification_Features_Extraction_Methods_A_Systematic_Review\u002Flinks\u002F599e2816aca272dff12fdef1\u002FSpeaker-Identification-Features-Extraction-Methods-A-Systematic-Review.pdf)方面的综述。\n然而，这些综述未涵盖本仓库包含的音乐信息检索（Music Information Retrieval）任务。\n\n## 目录\n\n- [DL4M 摘要](#dl4m-summary)\n- [DL4M 详情](#dl4m-details)\n- [无论文的代码](#code-without-articles)\n- [统计与可视化](#statistics-and-visualisations)\n- [DL4M论文审阅建议](#advices-for-reviewers-of-dl4m-articles)\n- [如何贡献](#how-to-contribute)\n- [常见问题](#faq)\n- [使用的缩写](#acronyms-used)\n- [来源](#sources)\n- [贡献者](#contributors)\n- [其他相关列表](#other-useful-related-lists-and-resources)\n- [被引用情况](#cited-by)\n- [许可证](#license)\n\n## DL4M 摘要\n\n| 年份 | 文章、论文和报告 | 代码 |\n|------|-------------------------------|------|\n| 1988 | 神经网络音乐建模 | 否 |\n| 1988 | [通过细化创造：梯度下降学习网络的创造力范式](http:\u002F\u002Fieeexplore.ieee.org\u002Fstamp\u002Fstamp.jsp?arnumber=23933) | 否 |\n| 1988 | 音乐应用的序列网络设计 | 否 |\n| 1989 | [神经网络和弦分类模型中的音高表示](http:\u002F\u002Fwww.jstor.org\u002Fstable\u002F3679550) | 否 |\n| 1989 | [神经网络音乐作曲算法：改进的CBR范式](https:\u002F\u002Fquod.lib.umich.edu\u002Fcgi\u002Fp\u002Fpod\u002Fdod-idx\u002Falgorithms-for-music-composition.pdf?c=icmc;idno=bbp2372.1989.044;format=pdf) | 否 |\n| 1989 | [算法作曲的联结主义方法](http:\u002F\u002Fwww.jstor.org\u002Fstable\u002F3679551) | 否 |\n| 1994 | [通过预测的神经网络音乐创作：探索听觉心理约束和多尺度处理的优势](http:\u002F\u002Fwww-labs.iro.umontreal.ca\u002F~pift6080\u002FH09\u002Fdocuments\u002Fpapers\u002Fmozer-music.pdf) | 否 |\n| 1995 | [单音色乐器声音的自动源识别](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F3622871_Automatic_source_identification_of_monophonic_musical_instrument_sounds) | 否 |\n| 1995 | [基于神经网络的音乐类型分类模型](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F514161\u002F) | 否 |\n| 1997 | [机器学习在音乐风格识别中的应用](http:\u002F\u002Frepository.cmu.edu\u002Fcgi\u002Fviewcontent.cgi?article=1496&context=compsci) | 否 |\n| 1998 | [音乐类型的识别](https:\u002F\u002Fwww.ri.cmu.edu\u002Fpub_files\u002Fpub1\u002Fsoltau_hagen_1998_2\u002Fsoltau_hagen_1998_2.pdf) | 否 |\n| 1999 | [音乐网络：并行分布式感知与表现](https:\u002F\u002Fs3.amazonaws.com\u002Facademia.edu.documents\u002F3551783\u002F10.1.1.39.6248.pdf?AWSAccessKeyId=AKIAIWOWYYGZ2Y53UL3A&Expires=1507055806&Signature=5mGzQc7bvJgUZYfXOmCX8eeNQOs%3D&response-content-disposition=inline%3B%20filename%3DMusical_networks_Parallel_distributed_pe.pdf) | 否 |\n| 2001 | [爵士即兴演奏与互动的多阶段学习](http:\u002F\u002Fwww.cs.smith.edu\u002F~jfrankli\u002Fpapers\u002FCtColl01.pdf) | 否 |\n| 2002 | [监督学习在音乐风格识别中的应用](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FGiuseppe_Buzzanca\u002Fpublication\u002F228588086_A_supervised_learning_approach_to_musical_style_recognition\u002Flinks\u002F54b43ee90cf26833efd0109f.pdf) | 否 |\n| 2002 | [在音乐中寻找时间结构：使用LSTM循环网络的蓝调即兴演奏](http:\u002F\u002Fwww-perso.iro.umontreal.ca\u002F~eckdoug\u002Fpapers\u002F2002_ieee.pdf) | 否 |\n| 2002 | [钢琴音乐中的音符起始检测神经网络](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FMatija_Marolt\u002Fpublication\u002F2473938_Neural_Networks_for_Note_Onset_Detection_in_Piano_Music\u002Flinks\u002F00b49525efccc79fed000000.pdf) | 否 |\n| 2004 | [基于卷积核的钢琴独奏音频信号音符起始检测方法](http:\u002F\u002Fwww.murase.nuie.nagoya-u.ac.jp\u002F~ide\u002Fres\u002Fpaper\u002FE04-conference-pablo-1.pdf) | 否 |\n| 2009 | [使用卷积深度信念网络的音频分类无监督特征学习](http:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F3674-unsupervised-feature-learning-for-audio-classification-using-convolutional-deep-belief-networks.pdf) | 否 |\n| 2010 | [使用卷积神经网络和音高、节奏变换的音频音乐流派分类](http:\u002F\u002Flbms03.cityu.edu.hk\u002Ftheses\u002Fc_ftt\u002Fmphil-cs-b39478026f.pdf) | 否 |\n| 2010 | [使用卷积神经网络的自动音乐模式特征提取](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FAntoni_Chan2\u002Fpublication\u002F44260643_Automatic_Musical_Pattern_Feature_Extraction_Using_Convolutional_Neural_Network\u002Flinks\u002F02e7e523dac6bb86b0000000.pdf) | 否 |\n| 2011 | [基于预训练卷积网络的音频音乐分类](http:\u002F\u002Fwww.ismir2011.ismir.net\u002Fpapers\u002FPS6-3.pdf) | 否 |\n| 2012 | [重新思考使用卷积神经网络的自动和弦识别](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F6406762\u002F) | 否 |\n| 2012 | [超越特征设计：音乐信息学中的深度架构和自动特征学习](http:\u002F\u002Fciteseerx.ist.psu.edu\u002Fviewdoc\u002Fdownload?doi=10.1.1.294.2304&rep=rep1&type=pdf) | 否 |\n| 2012 | [使用卷积神经网络进行局部特征图整合的音乐流派分类](http:\u002F\u002Fliris.cnrs.fr\u002FDocuments\u002FLiris-5602.pdf) | 否 |\n| 2012 | [用于音乐标注和检索的稀疏特征表示学习](https:\u002F\u002Fpdfs.semanticscholar.org\u002F099d\u002F85f25e9336f48ff64287a4b53ee5fb64ab51.pdf) | 否 |\n| 2012 | [用于音乐分类的无监督局部特征学习](http:\u002F\u002Fwww.ismir2012.ismir.net\u002Fevent\u002Fpapers\u002F139_ISMIR_2012.pdf) | 否 |\n| 2013 | [多尺度音乐音频特征学习方法](http:\u002F\u002Fismir2013.ismir.net\u002Fwp-content\u002Fuploads\u002F2013\u002F09\u002F69_Paper.pdf) | 否 |\n| 2013 | [使用卷积神经网络的音乐音符起始检测](http:\u002F\u002Fphenicx.upf.edu\u002Fsystem\u002Ffiles\u002Fpublications\u002FSchlueter_MML13.pdf) | 否 |\n| 2013 | [深度内容驱动的音乐推荐](http:\u002F\u002Fpapers.nips.cc\u002Fpaper\u002F5004-deep-content-based-music-recommendation.pdf) | 否 |\n| 2014 | [慕尼黑LSTM-RNN在MediaEval 2014音乐情感任务中的应用](https:\u002F\u002Fpdfs.semanticscholar.org\u002F8a24\u002Fc5131d5a28165f719697028c34b00e6d3f60.pdf) | 否 |\n| 2014 | [端到端音乐音频学习](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F6854950\u002F) | 否 |\n| 2014 | [深度学习在音乐流派分类中的应用](https:\u002F\u002Fcourses.engr.illinois.edu\u002Fece544na\u002Ffa2014\u002FTao_Feng.pdf) | 否 |\n| 2014 | [使用深度神经网络进行声学事件识别](https:\u002F\u002Fwww.cs.tut.fi\u002Fsgn\u002Farg\u002Fmusic\u002Ftuomasv\u002Fdnn_eusipco2014.pdf) | 否 |\n| 2014 | [深度图像特征在音乐信息检索中的应用](https:\u002F\u002Fwww.degruyter.com\u002Fdownloadpdf\u002Fj\u002Feletel.2014.60.issue-4\u002Feletel-2014-0042\u002Feletel-2014-0042.pdf) | 否 |\n| 2014 | [从音乐音频到和弦表格：教深度卷积网络弹吉他](https:\u002F\u002Fejhumphrey.com\u002Fassets\u002Fpdf\u002Fhumphrey2014music.pdf) | 否 |\n| 2014 | [改进的卷积神经网络音乐音符起始检测](http:\u002F\u002Fwww.mirlab.org\u002Fconference_papers\u002FInternational_Conference\u002FICASSP%202014\u002Fpapers\u002Fp7029-schluter.pdf) | 否 |\n| 2014 | [使用卷积神经网络进行音乐结构分析边界检测](https:\u002F\u002Fdav.grrrr.org\u002Fpublic\u002Fpub\u002Fullrich_schlueter_grill-2014-ismir.pdf) | 否 |\n| 2014 | [使用深度学习改进基于内容和混合音乐推荐](http:\u002F\u002Fwww.smcnus.org\u002Fwp-content\u002Fuploads\u002F2014\u002F08\u002Freco_MM14.pdf) | 否 |\n| 2014 | [用于不变性和音乐分类的深度表示](http:\u002F\u002Fwww.mirlab.org\u002Fconference_papers\u002FInternational_Conference\u002FICASSP%202014\u002Fpapers\u002Fp7034-zhang.pdf) | 否 |\n| 2015 | [深度卷积神经网络的听觉化：聆听学习特征](http:\u002F\u002Fismir2015.uma.es\u002FLBD\u002FLBD24.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi\u002FAuralisation) |\n| 2015 | [使用多种特征和深度神经网络的拍点追踪](http:\u002F\u002Fperso.telecom-paristech.fr\u002F~grichard\u002FPublications\u002F2015-durand-icassp.pdf) | 否 |\n| 2015 | [使用神经网络在频谱图和自相似滞后矩阵上进行音乐边界检测](http:\u002F\u002Fwww.ofai.at\u002F~jan.schlueter\u002Fpubs\u002F2015_eusipco.pdf) | 否 |\n| 2015 | [使用卷积神经网络对空间音频位置和内容进行分类](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FToni_Hirvonen\u002Fpublication\u002F276061831_Classification_of_Spatial_Audio_Location_and_Content_Using_Convolutional_Neural_Networks\u002Flinks\u002F5550665908ae12808b37fe5a\u002FClassification-of-Spatial-Audio-Location-and-Content-Using-Convolutional-Neural-Networks.pdf) | 否 |\n| 2015 | [深度学习、音频对抗与音乐内容分析](http:\u002F\u002Fwww2.imm.dtu.dk\u002Fpubdb\u002Fviews\u002Fedoc_download.php\u002F6905\u002Fpdf\u002Fimm6905.pdf) | 否 |\n| 2015 | [深度学习与音乐对抗](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1507.04761.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fcoreyker\u002Fdnn-mgr) |\n| 2015 | [使用深度循环神经网络的歌唱声检测](https:\u002F\u002Fhal-imt.archives-ouvertes.fr\u002Fhal-01110035\u002F) | 否 |\n| 2015 | [使用卷积神经网络进行多音音乐中乐器的自动识别](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1511.05520.pdf) | 否 |\n| 2015 | [音乐数据增强的软件框架](https:\u002F\u002Fbmcfee.github.io\u002Fpapers\u002Fismir2015_augmentation.pdf) | 否 |\n| 2015 | [用于音乐自动标记的深度词袋模型](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1508.04999v1.pdf) | 否 |\n| 2015 | [使用卷积神经网络在时空域进行音乐-噪声分割](http:\u002F\u002Fismir2015.uma.es\u002FLBD\u002FLBD27.pdf) | 否 |\n| 2015 | [使用特征融合方法的深度卷积神经网络进行乐器声音分类](https:\u002F\u002Farxiv.org\u002Fftp\u002Farxiv\u002Fpapers\u002F1512\u002F1512.07370.pdf) | 否 |\n| 2015 | [使用卷积神经网络进行环境声音分类](http:\u002F\u002Fkarol.piczak.com\u002Fpapers\u002FPiczak2015-ESC-ConvNet.pdf) | 否 |\n| 2015 | [探索数据增强以改进神经网络的歌唱声检测](https:\u002F\u002Fgrrrr.org\u002Fpub\u002Fschlueter-2015-ismir.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Ff0k\u002Fismir2015) |\n| 2015 | [使用深度神经网络识别歌手特征](https:\u002F\u002Fcs224d.stanford.edu\u002Freports\u002FSkiZhengshan.pdf) | 否 |\n| 2015 | [混合循环神经网络用于音乐转录](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1411.1623.pdf) | 否 |\n| 2015 | [用于多音音乐转录的端到端神经网络](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1508.01774.pdf) | 否 |\n| 2015 | [深度卡拉OK：使用卷积深度神经网络从音乐混合中提取人声](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-22482-4_50) | 否 |\n| 2015 | [使用长短期记忆单元的循环神经网络进行民间音乐风格建模](http:\u002F\u002Fismir2015.uma.es\u002FLBD\u002FLBD13.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FIraKorshunova\u002Ffolk-rnn) |\n| 2015 | [基于深度神经网络的音乐中乐器提取](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FStefan_Uhlich\u002Fpublication\u002F282001406_Deep_neural_network_based_instrument_extraction_from_music\u002Flinks\u002F5600eeda08ae07629e52b397\u002FDeep-neural-network-based-instrument-extraction-from-music.pdf) | 否 |\n| 2015 | [用于音乐建模的深度神经网络](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FXiaoqing_Zheng3\u002Fpublication\u002F275347034_A_Deep_Neural_Network_for_Modeling_Music\u002Flinks\u002F5539d2060cf2239f4e7dad0d\u002FA-Deep-Neural-Network-for-Modeling-Music.pdf) | 否 |\n| 2016 | [一种高效的音频信号分割、特征提取和分类方法](http:\u002F\u002Ffile.scirp.org\u002Fpdf\u002FCS_2016042615054817.pdf) | 否 |\n| 2016 | [基于LSTM网络的文本驱动自动音乐创作](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F0B1OooSxEtl0FcG9MYnY2Ylh5c0U\u002Fview) | 否 |\n| 2016 | [使用基于曲目内转换的RNN生成播放列表的算法](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1606.02096.pdf) | 否 |\n| 2016 | [自动标记的深度卷积神经网络](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1606.00298.pdf) | 否 |\n| 2016 | [使用深度神经网络进行七和弦词汇的自动和弦估计](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7471677\u002F) | 否 |\n| 2016 | [DeepBach：巴赫合唱曲生成的可导向模型](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1612.01010.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FGhadjeres\u002FDeepBach) |\n| 2016 | [基于学习信号表示的贝叶斯节拍跟踪](http:\u002F\u002Fwww.rhythmos.org\u002FMMILab-Andre_files\u002FISMIR2016_CNNDBNbeats_camready.pdf) | 否 |\n| 2016 | [深度学习在音乐中的应用](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1606.04930.pdf) | 否 |\n| 2016 | [使用深度神经网络学习时间特征及其在音乐流派分类中的应用](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FIl_Young_Jeong\u002Fpublication\u002F305683876_Learning_temporal_features_using_a_deep_neural_network_and_its_application_to_music_genre_classification\u002Flinks\u002F5799a27c08aec89db7bb9f92.pdf) | 否 |\n| 2016 | [钢琴转录中简单帧级方法的潜力](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1612.05153.pdf) | 否 |\n| 2016 | [和弦识别的特征学习：深度色度提取器](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1612.05065.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Ffdlm\u002Fchordrec\u002Ftree\u002Fmaster\u002Fexperiments\u002Fismir2016) |\n| 2016 | [用于音乐和弦识别的全卷积深度听觉模型](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FFilip_Korzeniowski\u002Fpublication\u002F305590295_A_Fully_Convolutional_Deep_Auditory_Model_for_Musical_Chord_Recognition\u002Flinks\u002F579486ba08aed51475cc6958\u002FA-Fully-Convolutional-Deep-Auditory-Model-for-Musical-Chord-Recognition.pdf?_iepl%5BhomeFeedViewId%5D=HTzFFmKPia2YminQ4psHT5at&_iepl%5Bcontexts%5D%5B0%5D=pcfhf&_iepl%5BinteractionType%5D=publicationDownload&origin=publication_detail&ev=pub_int_prw_xdl&msrp=Dz_6LKHzYcPyP-LmgZPF-m63ayZ6k0entFEntooiu_e32zfETNQXKPQSTFOI87NONIIQuUQdnUtwORdomTXfteTrb09KiAIdDtBJnw_02P6JeRr5zu2eyaCG.2Uxsi_eENxtbYL39lvorIK8LofRYhkgpUHzpzmVzkIEiyHc0wUY87rEa4PH1qbXi4k4RyagHUsA2IsZtewnprglORjx2v9Cwbk9ZfQ.cd67BaqtHul_hE6SX6vUFKuldz81aH6dWq-cYMkq5vQKCHcvB8l9zgeM694Efb_r2wBB5GT9idt3OLeME0UxVHI6ROxamgK3LMNlSw.JtZXAo9HhR9t-8Wl3gxJgnoM4--rtmDEUDbXSWezbFyU-CoB_nyfxbRQ4kdoN4-5aJ3Tgx4YHdikicqAhc_cezB2ZntjxkB4rEDx1A) | 否 |\n| 2016 | [基于深度双向长短期记忆的多尺度方法用于音乐动态情感预测](http:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F7471734\u002F) | 否 |\n| 2016 | [音乐自动标记中的事件定位](http:\u002F\u002Fmac.citi.sinica.edu.tw\u002F~yang\u002Fpub\u002Fliu16mm.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fciaua\u002Fclip2frame) |\n| 2016 | [基于音高螺旋的深度卷积网络用于乐器识别](https:\u002F\u002Fgithub.com\u002Flostanlen\u002Fismir2016\u002Fblob\u002Fmaster\u002Fpaper\u002Flostanlen_ismir2016.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Flostanlen\u002Fismir2016) |\n| 2016 | [SampleRNN：无条件端到端神经音频生成模型](https:\u002F\u002Fopenreview.net\u002Fpdf?id=SkxKPDv5xl) | [GitHub](https:\u002F\u002Fgithub.com\u002Fsoroushmehr\u002FsampleRNN_ICLR2017) |\n| 2016 | [使用1-max池化卷积神经网络的鲁棒音频事件识别](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1604.06338.pdf) | 否 |\n| 2016 | [基于音乐动机的卷积神经网络实验](http:\u002F\u002Fjordipons.me\u002Fmedia\u002FCBMI16.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fjordipons\u002F) |\n| 2016 | [使用深度神经网络的歌唱旋律转录](https:\u002F\u002Fwp.nyu.edu\u002Fismir2016\u002Fwp-content\u002Fuploads\u002Fsites\u002F2294\u002F2016\u002F07\u002F163_Paper.pdf) | 否 |\n| 2016 | [使用深度神经网络和F0估计的歌唱声分离](http:\u002F\u002Fwww.music-ir.org\u002Fmirex\u002Fabstracts\u002F2016\u002FRSGP1.pdf) | [网站](http:\u002F\u002Fcvssp.org\u002Fprojects\u002Fmaruss\u002Fmirex2016\u002F) |\n| 2016 | [从弱标记示例中定位歌唱声](http:\u002F\u002Fwww.ofai.at\u002F~jan.schlueter\u002Fpubs\u002F2016_ismir.pdf) | 否 |\n| 2016 | [使用卷积神经网络分析时频表示进行音乐起始检测](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7733228\u002F) | 否 |\n| 2016 | [基于神经网络的多ODF融合进行音乐信号音符起始检测](https:\u002F\u002Fwww.degruyter.com\u002Fdownloadpdf\u002Fj\u002Famcs.2016.26.issue-1\u002Famcs-2016-0014\u002Famcs-2016-0014.pdf) | 否 |\n| 2016 | [使用深度学习进行音乐转录建模和创作](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F0B1OooSxEtl0FcTBiOGdvSTBmWnc\u002Fview) | [GitHub](https:\u002F\u002Fgithub.com\u002FIraKorshunova\u002Ffolk-rnn) |\n| 2016 | [用于鲁棒音高确定的卷积神经网络](http:\u002F\u002Fwww.mirlab.org\u002Fconference_papers\u002FInternational_Conference\u002FICASSP%202016\u002Fpdfs\u002F0000579.pdf) | 否 |\n| 2016 | [深度卷积神经网络和数据增强在声学事件检测中的应用](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1604.07160.pdf) | [网站](https:\u002F\u002Fbitbucket.org\u002Fnaoya1\u002Faenet_release) |\n| 2017 | [音频处理中的Gabor帧和深度散射网络](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.08818.pdf) | 否 |\n| 2017 | [基于视觉的声学定时事件检测：单簧管音符起始的案例研究](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fbazzica2017clarinet.pdf) | 否 |\n| 2017 | [深度学习在音乐生成中的技术综述](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.01620.pdf) | 否 |\n| 2017 | [JamBot：基于LSTM的音乐理论感知和弦多音音乐生成](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1711.07682.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fbrunnergino\u002FJamBot) |\n| 2017 | [XFlow：用于音视频分类的1D\u003C->2D跨模态深度神经网络](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.00572.pdf) | 否 |\n| 2017 | [机器听觉智能](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fcella2017mli.pdf) | 否 |\n| 2017 | [使用深度卷积神经网络的单耳音频源分离](http:\u002F\u002Fmtg.upf.edu\u002Fsystem\u002Ffiles\u002Fpublications\u002Fmonoaural-audio-source_0.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FMTG\u002FDeepConvSep) |\n| 2017 | [多标签分类的深度多模态网络](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8019322\u002F) | 否 |\n| 2017 | [深度学习在音乐信息检索中的教程](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.04396.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi\u002Fdl4mir) |\n| 2017 | [音乐标记中音频信号预处理方法的比较](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.01922.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi\u002Ftransfer_learning_music) |\n| 2017 | [音乐分类和回归任务的迁移学习](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.09179v3.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi\u002Ftransfer_learning_music) |\n| 2017 | [用于音乐分类的卷积循环神经网络](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7952585\u002F) | [GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi\u002Ficassp_2017) |\n| 2017 | [使用频谱图评估卷积神经网络在音乐分类中的应用](http:\u002F\u002Fwww.inf.ufpr.br\u002Flesoliveira\u002Fdownload\u002FASOC2017.pdf) | 否 |\n| 2017 | [基于深度神经网络的大词汇量自动和弦估计：设计框架、系统变体和局限性](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.07153.pdf) | 否 |\n| 2017 | [卷积神经网络的基本滤波器：训练还是设计？](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.02291.pdf) | 否 |\n| 2017 | [用于声学场景分类的深度神经网络集成](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1708.05826.pdf) | 否 |\n| 2017 | [使用卷积网络集成的鲁棒拍点跟踪](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F7728057\u002F) | 否 |\n| 2017 | [使用向量乘积神经网络进行音乐信号处理](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Ffan2017vector.pdf) | 否 |\n| 2017 | [通过流派分类卷积神经网络转换音乐信号](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fgeng2017genre.pdf) | 否 |\n| 2017 | [通过结合语音和时长信息进行音频到乐谱匹配](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.03547.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fronggong\u002FjingjuSingingPhraseMatching\u002Ftree\u002Fv0.1.0) |\n| 2017 | [使用前瞻性RNN进行带位置约束的交互式音乐生成](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.06404.pdf) | 否 |\n| 2017 | [基于深度排名的音乐序列转置不变距离](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1709.00740.pdf) | 否 |\n| 2017 | [GLSR-VAE：变分自编码器架构的测地线潜在空间正则化](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.04588.pdf) | 否 |\n| 2017 | [用于多音音乐中主要乐器识别的深度卷积神经网络](http:\u002F\u002Fdl.acm.org\u002Fcitation.cfm?id=3068697) | 否 |\n| 2017 | [大规模音频分类的CNN架构](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1609.09430v2.pdf) | 否 |\n| 2017 | [DeepSheet：基于深度学习的乐谱生成器](http:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8026272\u002F) | 否 |\n| 2017 | [Talking Drums：使用神经网络生成鼓节奏](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fhutchings2017drums.pdf) | 否 |\n| 2017 | [使用深度U-Net卷积网络进行歌唱声分离](https:\u002F\u002Fismir2017.smcnus.org\u002Fwp-content\u002Fuploads\u002F2017\u002F10\u002F171_Paper.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FXiao-Ming\u002FUNet-VocalSeparation-Chainer) |\n| 2017 | [基于端到端多模态神经网络的音乐情感识别](http:\u002F\u002Fceur-ws.org\u002FVol-1905\u002Frecsys2017_poster18.pdf) | 否 |\n| 2017 | [通过深度学习集成和声间隔表示进行和弦标签个性化](http:\u002F\u002Fdorienherremans.com\u002Fdlm2017\u002Fpapers\u002Fkoops2017pers.pdf) | 否 |\n| 2017 | [使用卷积神经网络进行端到端音乐调性估计](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.02921.pdf) | 否 |\n| 2017 | [MediaEval 2017 AcousticBrainz流派任务：多层感知机方法](http:\u002F\u002Fwww.cp.jku.at\u002Fresearch\u002Fpapers\u002FKoutini_2017_mediaeval-acousticbrainz.pdf) | 否 |\n| 2017 | [基于深度卷积神经网络的分类歌唱旋律提取](https:\u002F\u002Fwww.preprints.org\u002Fmanuscript\u002F201711.0027\u002Fv1) | 否 |\n| 2017 | [使用预训练卷积神经网络进行多级多尺度特征聚合的音乐自动标记](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.01793v2.pdf) | 否 |\n| 2017 | [使用样本级深度卷积神经网络进行多级多尺度特征聚合的音乐分类](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.06810.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002Fjongpillee\u002FmusicTagging_MSD) |\n| 2017 | [使用原始波形的样本级深度卷积神经网络进行音乐自动标记](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1703.01789v2.pdf) | 否 |\n| 2017 | [用于多音音乐生成的SeqGAN](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1710.11418.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FL0SG\u002Fseqgan-music) |\n| 2017 | [使用卷积自编码器进行和声与打击乐源分离](http:\u002F\u002Fwww.eurasip.org\u002FProceedings\u002FEusipco\u002FEusipco2017\u002Fpapers\u002F1570346835.pdf) | 否 |\n| 2017 | [用于音乐情感识别的堆叠卷积和循环神经网络](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.02292.pdf) | 否 |\n| 2017 | [嘻哈音乐源分离和混音的深度学习方法](https:\u002F\u002Frepositori.upf.edu\u002Fbitstream\u002Fhandle\u002F10230\u002F32919\u002FMartel_2017.pdf?sequence=1&isAllowed=y) | 否 |\n| 2017 | [使用掩码条件神经网络的音乐流派分类](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007%2F978-3-319-70096-0_49) | 否 |\n| 2017 | [使用跳跃过滤连接和时间频率掩码递归推理的单声道歌唱声分离](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1711.01437.pdf) | [GitHub](https:\u002F\u002Fgithub.com\u002FJs-Mim\u002Fmss_pytorch) |\n| 2017 | [生成数据以训练用于古典音乐源分离的卷积神经网络](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FMarius_Miron\u002Fpublication\u002F318322107_Generating_data_to_train_convolutional_neural_networks_for_classical_music_source_separation\u002Flinks\u002F59637cc3458515a3575b93c6\u002FGenerating-data-to-train-convolutional-neural-networks-for-classical-music-source-separation.pdf?_iepl%5BhomeFeedViewId%5D=WchoMnlUL1Hk9hBLVTeR8Amh&_iepl%5Bcontexts%5D%5B0%5D=pcfhf&_iepl%5BinteractionType%5D=publicationDownload&origin=publication_detail&ev=pub_int_prw_xdl&msrp=p3lQ8M4uZlb4TF5Hv9a2U3P2y4wW7ant5KWj4E5-OcD1Mg53p1ykTKHMG9_zVTB9n6mI8fvZOCL2Xhpru186pCEY-2ZxiYR-CB8_QvwHc1kUG-QE4SHdProR.LoJb2BDOiiQth3iR9xgZUxxCWEJgtTBF4whFrFa01OD49-3YYRxA0WQVN--zhtQU_7C2Pt0rKdwoFxT1pfxFvnKXSXmy2eT1Jpz-pw.U1QLoFO_Uc6aQVr2Nm2FcAi6BqAUfngH2Or5__6wegbCgVvTYoIGt22tmCkYbGTOQ_4PxBgt1LrvsFQiL0oMyogP8Yk8myTj0gs9jw.fGpkufGqAI4R2v8Hfe0ThcXL7M7yN2PuAlx974BGVn50SdUWvNhhIPWBD-zWTn8NKtVJx3XrjKXFrMgi9Cx7qGrNP8tBWpha6Srf6g) | [GitHub](https:\u002F\u002Fgithub.com\u002FMTG\u002FDeepConvSep)\n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n\n\n## DL4M 详细信息\n\n一个可读性更强的表格汇总版本显示在文件 [dl4m.tsv](dl4m.tsv) 中。每篇文章的完整细节存储在对应的 BibTeX 条目（bib entry）中，位于 [dl4m.bib](dl4m.bib)。每个条目包含标准的 bib 字段：\n\n- `author`\n- `year`\n- `title`\n- `journal` 或 `booktitle`\n\n[dl4m.bib](dl4m.bib) 中的每个条目还包含额外信息：\n\n- `link` - PDF 文件的 HTML 链接\n- `code` - 可用的源代码链接\n- `archi` - 神经网络架构（Neural Network Architecture）\n- `layer` - 层数\n- `task` - 文章中研究的提出任务\n- `dataset` - 使用的数据集名称\n- `dataaugmentation` - 使用的数据增强技术类型\n- `time` - 计算时间\n- `hardware` - 使用的硬件\n- `note` - 额外说明和信息\n- `repro` - 实验可重复性的程度说明\n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## 无关联论文的代码项目\n\n- [使用卷积神经网络（Convolutional Neural Network, CNN）的音频分类器（Keras 实现）](https:\u002F\u002Fgithub.com\u002Fdrscotthawley\u002Faudio-classifier-keras-cnn)\n- [使用 Keras & Theano 的爵士乐生成深度学习模型](https:\u002F\u002Fgithub.com\u002Fjisungk\u002Fdeepjazz)\n- [大规模音乐音频标签的端到端学习](https:\u002F\u002Fgithub.com\u002Fjordipons\u002Fmusic-audio-tagging-at-scale-models)\n- [使用 CNN 在 GTZAN 数据集上的音乐流派分类](https:\u002F\u002Fgithub.com\u002FHguimaraes\u002Fgtzan.keras)\n- [基于深度学习策略的合唱音乐音高估计：从独唱到齐唱录音](https:\u002F\u002Fgithub.com\u002Fhelenacuesta\u002Fchoir-pitch-estimation)\n- [使用 LSTM 的音乐流派分类](https:\u002F\u002Fgithub.com\u002Fruohoruotsi\u002FLSTM-Music-Genre-Classification)\n- [使用 TensorFlow 的基于 CNN 的音乐情感分类](https:\u002F\u002Fgithub.com\u002Frickiepark\u002Fcnn_mer)\n- [基于 Tensorflow 的深度神经网络实现的歌声人声分离](https:\u002F\u002Fgithub.com\u002Fandabi\u002Fmusic-source-separation)\n- [使用 CRNN 的音乐标签分类模型](https:\u002F\u002Fgithub.com\u002Fkristijanbartol\u002FDeep-Music-Tagger)\n- [使用深度学习确定歌曲流派](https:\u002F\u002Fgithub.com\u002Fdespoisj\u002FDeepAudioClassification)\n- [使用神经网络作曲](https:\u002F\u002Fgithub.com\u002Ffephsun\u002Fneuralnetmusic)\n- [Performance-RNN-PyTorch](https:\u002F\u002Fgithub.com\u002Fdjosix\u002FPerformance-RNN-PyTorch)\n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## 统计数据与可视化\n\n- 引用了 167 篇论文。详情见 [dl4m.bib](dl4m.bib)。\n2017 年的论文数量超过其他年份的总和。\n按年份划分的文章数量：\n![每年的文章数量](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_4b3e5a139a32.png)\n- 如果你正在应用深度学习（Deep Learning, DL）进行音乐研究，那么还有 [364 位其他研究者](authors.md) 在这个领域。\n- 调查了 34 项任务。任务列表见 [tasks](tasks.md)。\n任务饼图：\n![任务饼图](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_b37647cd735a.png)\n- 使用了 55 个数据集。数据集列表见 [datasets](datasets.md)。\n数据集饼图：\n![数据集饼图](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_1feb58db0c7b.png)\n- 使用了 30 种架构。架构列表见 [architectures](architectures.md)。\n架构饼图：\n![架构饼图](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_39713cf04823.png)\n- 使用了 9 种框架。框架列表见 [frameworks](frameworks.md)。\n框架饼图：\n![框架饼图](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_readme_aff3848209e7.png)\n- 仅有 47 篇文章（28%）提供了源代码。\n可重复性是科学的关键，因此请查看 [MIR 和 ML 领域可重复性的有用资源列表](reproducibility.md)。\n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## dl4m 论文审阅建议\n\n请参考 [advice_review.md](advice_review.md) 文件。\n\n## 如何贡献\n\n欢迎贡献！\n请参考 [CONTRIBUTING.md](CONTRIBUTING.md) 文件。\n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## 常见问题\n\n> 文章是如何排序的？\n\n文章首先按年份降序排列（以便紧跟最新动态），然后按主要作者的姓氏字母顺序排列。\n\n> 为什么 arXiv 的预印本包含在列表中？\n\n我希望对 DL4M 进行全面研究并获取最新动态。然而，应注意当前处于评审中的文章信息。如果可能，请等待最终被接受并经过同行评审的版本后再引用 arXiv 论文。我会定期更新 arXiv 链接为已发表的论文链接（如果可用）。\n\n> 我能信任文章中发表的结果吗？\n\n此处提供的列表不保证文章的质量。您应尝试重现描述的实验，或向 [ReScience](https:\u002F\u002Fgithub.com\u002FReScience\u002FReScience) 提交请求。使用一篇文章的结论需自行承担风险。\n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## 使用的缩写\n\n深度学习和音乐领域常用缩写列表存储在 [acronyms.md](acronyms.md) 中。\n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## 来源\n\n用于收集所列材料的会议、期刊和聚合器列表存储在 [sources.md](sources.md) 中。\n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## 贡献者\n\n- [Yann Bayle](http:\u002F\u002Fyannbayle.fr\u002Fenglish\u002Findex.php) ([GitHub](https:\u002F\u002Fgithub.com\u002Fybayle)) - 发起人和主要维护者\n- Vincent Lostanlen ([GitHub](https:\u002F\u002Fgithub.com\u002Flostanlen))\n- [Keunwoo Choi](https:\u002F\u002Fkeunwoochoi.wordpress.com\u002F) ([GitHub](https:\u002F\u002Fgithub.com\u002Fkeunwoochoi))\n- [Bob L. Sturm](http:\u002F\u002Fwww.eecs.qmul.ac.uk\u002F~sturm\u002F) ([GitHub](https:\u002F\u002Fgithub.com\u002Fboblsturm))\n- [Stefan Balke](https:\u002F\u002Fwww.audiolabs-erlangen.de\u002Ffau\u002Fassistant\u002Fbalke) ([GitHub](https:\u002F\u002Fgithub.com\u002Fstefan-balke))\n- [Jordi Pons](http:\u002F\u002Fwww.jordipons.me\u002F) ([GitHub](https:\u002F\u002Fgithub.com\u002Fjordipons))\n- Mirza Zulfan ([GitHub](https:\u002F\u002Fgithub.com\u002Fmirzazulfan)) 为项目设计了标志\n- [Devin Walters](https:\u002F\u002Fgithub.com\u002Fdevn)\n- https:\u002F\u002Fgithub.com\u002FLegendJ\n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## 其他有用的列表和资源\n\n#### 音频\n\n- [使用Keras的DL4MIR教程](https:\u002F\u002Fgithub.com\u002Ftuwien-musicir\u002FDL_MIR_Tutorial) - 由[Thomas Lidy](http:\u002F\u002Fifs.tuwien.ac.at\u002F~lidy\u002F)提供的音乐信息检索（MIR）深度学习（Deep Learning）教程  \n- [Ron Weiss的视频演讲](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=sI_8EA0_ha8) - Ron Weiss（Google）关于在波形（waveforms）上训练神经网络声学模型（Acoustic models）的演讲  \n- [DL4M幻灯片](http:\u002F\u002Fwww.jordipons.me\u002Fmedia\u002FDL4Music_Pons.pdf) - [Jordi Pons](http:\u002F\u002Fwww.jordipons.me\u002F)对当前技术的个人（重新）审视  \n- [DL4MIR教程](https:\u002F\u002Fgithub.com\u002Fmarl\u002Fdl4mir-tutorial) - Python教程，学习使用深度学习解决MIR任务  \n- [Awesome Python科学音频](https:\u002F\u002Fgithub.com\u002Ffaroit\u002Fawesome-python-scientific-audio) - 音频与机器学习的Python资源  \n- [ISMIR资源](http:\u002F\u002Fismir.net\u002Fresources.php) - 社区维护的资源列表  \n- [ISMIR Google群组](https:\u002F\u002Fgroups.google.com\u002Fa\u002Fismir.net\u002Fforum\u002F#!forum\u002Fcommunity) - 每日MIR通用话题  \n- [Awesome Python](https:\u002F\u002Fgithub.com\u002Fvinta\u002Fawesome-python#audio) - Python资源中的音频部分  \n- [Awesome Web Audio](https:\u002F\u002Fgithub.com\u002Fnotthetup\u002Fawesome-webaudio) - WebAudio包和资源  \n- [Awesome Music](https:\u002F\u002Fgithub.com\u002Fciconia\u002Fawesome-music) - 音乐软件  \n- [Awesome Music Production](https:\u002F\u002Fgithub.com\u002Fadius\u002Fawesome-music-production) - 音乐创作  \n- [Asimov研究所](http:\u002F\u002Fwww.asimovinstitute.org\u002Fanalyzing-deep-learning-tools-music\u002F) - 6个用于音乐生成的深度学习工具  \n- [DLM Google群组](https:\u002F\u002Fgroups.google.com\u002Fforum\u002F#!forum\u002Ficdlm) - 音乐领域的深度学习群组  \n- [Slack上的MIR社区](https:\u002F\u002Fslackpass.io\u002Fmircommunity) - 订阅MIR社区Slack的链接  \n- [未分类的MIR相关链接列表](http:\u002F\u002Fwww.music.mcgill.ca\u002F~cmckay\u002Flinks_academic.html) - [Cory McKay](http:\u002F\u002Fwww.music.mcgill.ca\u002F~cmckay\u002F)整理的深度学习、MIR等各类链接  \n- [MIRDL](http:\u002F\u002Fjordipons.me\u002Fwiki\u002Findex.php\u002FMIRDL) - [Jordi Pons](http:\u002F\u002Fwww.jordipons.me\u002F)整理的MIR深度学习文章列表（已不再维护）  \n- [WWW 2018挑战赛](https:\u002F\u002Fwww.crowdai.org\u002Fchallenges\u002Fwww-2018-challenge-learning-to-recognize-musical-genre) - 在[FMA](https:\u002F\u002Fgithub.com\u002Fmdeff\u002Ffma)数据集上学习识别音乐流派  \n- [使用深度学习的音乐生成](https:\u002F\u002Fgithub.com\u002Fumbrellabeach\u002Fmusic-generation-with-DL) - 深度学习音乐生成资源列表  \n- [听觉场景分析（Auditory Scene Analysis）](https:\u002F\u002Fmitpress.mit.edu\u002Fbooks\u002Fauditory-scene-analysis) - 由[Albert Bregman](https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FAlbert_Bregman)撰写的关于声音感知组织的书籍，他是“听觉场景分析（Auditory Scene Analysis）”的奠基人。  \n  - [听觉场景分析演示](http:\u002F\u002Fwebpages.mcgill.ca\u002Fstaff\u002FGroup2\u002Fabregm1\u002Fweb\u002Fdownloadstoc.htm) - 展示听觉感知组织示例的音频演示  \n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n#### 音乐数据集\n\n- [AudioContentAnalysis 几乎涵盖所有音乐相关数据集的列表](http:\u002F\u002Fwww.audiocontentanalysis.org\u002Fdata-sets\u002F)  \n- [教学MIR](https:\u002F\u002Fteachingmir.wikispaces.com\u002FDatasets)  \n- [维基百科的机器学习研究数据集列表](https:\u002F\u002Fen.wikipedia.org\u002Fwiki\u002FList_of_datasets_for_machine_learning_research#cite_ref-215)  \n- [深度学习数据集](http:\u002F\u002Fdeeplearning.net\u002Fdatasets\u002F)  \n- [Awesome公共数据集](https:\u002F\u002Fgithub.com\u002Fcaesar0301\u002Fawesome-public-datasets)  \n- [Awesome音乐聆听](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-music-listening)  \n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n#### 深度学习\n\n- [DLPaper2Code: 从深度学习研究论文中自动生成代码（Auto-generation of Code from Deep Learning Research Papers）](https:\u002F\u002Farxiv.org\u002Fabs\u002F1711.03543)  \n- [Model Convertors](https:\u002F\u002Fgithub.com\u002Fysh329\u002Fdeep-learning-model-convertor) - 深度学习框架和后端的模型转换工具（Convertors for DL frameworks and backend）  \n- [Deep architecture genealogy](https:\u002F\u002Fgithub.com\u002Fhunkim\u002Fdeep_architecture_genealogy) - 深度学习架构的谱系图（Genealogy of DL architectures）  \n- [Deep Learning as an Engineer](http:\u002F\u002Fwww.univie.ac.at\u002Fnuhag-php\u002Fdateien\u002Ftalks\u002F3358_schlueter.pdf) - Jan Schlüter 的演讲幻灯片（Slides from Jan Schlüter）  \n- [Awesome Deep Learning](https:\u002F\u002Fgithub.com\u002FChristosChristofidis\u002Fawesome-deep-learning) - 通用深度学习资源（General deep learning resources）  \n- [Awesome Deep Learning Resources](https:\u002F\u002Fgithub.com\u002Fendymecy\u002Fawesome-deeplearning-resources) - 关于深度学习和深度强化学习的论文（Papers regarding deep learning and deep reinforcement learning）  \n- [Awesome RNNs](https:\u002F\u002Fgithub.com\u002Fkjw0612\u002Fawesome-rnn) - 循环神经网络（RNNs）的代码、理论和应用（RNNs code, theory and applications）  \n- [Cheatsheets AI](https:\u002F\u002Fgithub.com\u002Fkailashahirwar\u002Fcheatsheets-ai) - Keras、神经网络、scikit-learn 等速查表（Cheat Sheets for Keras, neural networks, scikit-learn,...）  \n- [DL PaperNotes](https:\u002F\u002Fgithub.com\u002Fdennybritz\u002Fdeeplearning-papernotes) - 通用深度学习研究论文的摘要和笔记（Summaries and notes on general deep learning research papers）  \n- 通用 [![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome) 资源列表（General [![Awesome](...)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome) lists）  \n- [Echo State Network](http:\u002F\u002Fminds.jacobs-university.de\u002Fsites\u002Fdefault\u002Ffiles\u002Fuploads\u002Fpapers\u002FPracticalESN.pdf)  \n- [DL in NLP](http:\u002F\u002Fruder.io\u002Fdeep-learning-nlp-best-practices\u002Findex.html#introduction) - 使用神经网络的最佳实践（Best practices for using neural networks by [Sebastian Ruder](http:\u002F\u002Fruder.io\u002F)）  \n- [CNN overview](http:\u002F\u002Fcs231n.github.io\u002Fconvolutional-networks\u002F) - 斯坦福课程（Stanford Course）  \n- [Dilated Recurrent Neural Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1710.02224.pdf) - 如何改进循环神经网络（RNNs）？（How to improve RNNs?）  \n- [Encoder-Decoder in RNNs（编码器-解码器在 RNNs 中的应用）](https:\u002F\u002Fmachinelearningmastery.com\u002Fhow-does-attention-work-in-encoder-decoder-recurrent-neural-networks\u002F?utm_content=buffer0d2a7&utm_medium=social&utm_source=twitter.com&utm_campaign=bufferhttps:\u002F\u002Fblog.recast.ai\u002Fml-spotlight-rnn\u002F?utm_content=bufferf19d3&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer) - 编码器-解码器循环神经网络中的注意力机制（How Does Attention Work in Encoder-Decoder Recurrent Neural Networks）  \n- [On the use of DL](https:\u002F\u002Ftwitter.com\u002Frandal_olson\u002Fstatus\u002F927157485240311808\u002Fphoto\u002F1) - 关于深度学习的趣味内容（Misc fun around DL）  \n- [ML from scratch](https:\u002F\u002Fgithub.com\u002Feriklindernoren\u002FML-From-Scratch) - 从数据挖掘到深度学习的机器学习模型和算法的 Python 实现（Python implementations of ML models and algorithms from scratch from Data Mining to DL）  \n- [Comparison of DL frameworks](https:\u002F\u002Fproject.inria.fr\u002Fdeeplearning\u002Ffiles\u002F2016\u002F05\u002FDLFrameworks.pdf) - 描述现有深度学习框架的演示文稿（Presentation describing the different existing frameworks for DL）  \n- [ELU > ReLU](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1511.07289.pdf) - 描述 ELU 和 ReLU 之间差异的文章（Article describing the differences between ELU and ReLU）  \n- [Reinforcement Learning: An Introduction](http:\u002F\u002Fincompleteideas.net\u002Fsutton\u002Fbook\u002Fbookdraft2017nov5.pdf) - 强化学习入门书籍（Book about reinforcement learning）  \n- [Estimating Optimal Learning Rate](https:\u002F\u002Ftowardsdatascience.com\u002Festimating-optimal-learning-rate-for-a-deep-neural-network-ce32f2556ce0) - 关于学习率优化的博客文章（Blog post on the learning rate optimisation）  \n- [GitHub repo for sklearn add-on for imbalanced learning](https:\u002F\u002Fgithub.com\u002Fscikit-learn-contrib\u002Fimbalanced-learn) - 处理不平衡数据集的机器学习（ML in uneven datasets）  \n- [Video on DL from Nando de Freitas, Scott Reed and Oriol Vinyals](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=YJnddoa8sHk) - 深度学习：实践与趋势（NIPS 2017 教程，第一部分和第二部分）（Deep Learning: Practice and Trends (NIPS 2017 Tutorial, parts I & II)）  \n- [Article \"Are GANs Created Equal? A Large-Scale Study\"](https:\u002F\u002Farxiv.org\u002Fabs\u002F1711.10337) - 对比深度学习算法的实际研究（Actually comparing DL algorithms）  \n- [Battle of the Deep Learning frameworks](https:\u002F\u002Ftowardsdatascience.com\u002Fbattle-of-the-deep-learning-frameworks-part-i-cff0e3841750) - 深度学习框架的对比与演进（DL frameworks comparison and evolution）  \n- [Black-box optimization](http:\u002F\u002Ftimvieira.github.io\u002Fblog\u002Fpost\u002F2018\u002F03\u002F16\u002Fblack-box-optimization\u002F) - 除了梯度下降之外的其他优化算法（There are other optimization algorithms than just gradient descent）  \n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## 被引用情况（Cited by）\n\n如果您使用了本仓库中的信息，请告知我们！本仓库已被以下内容引用：\n\n- [Alexander Schindler](https:\u002F\u002Ftwitter.com\u002FSlychief\u002Fstatus\u002F915218386421997568)  \n- [Meinard Müller, Christof Weiss, Stefan Balke](https:\u002F\u002Fwww.audiolabs-erlangen.de\u002Fresources\u002FMIR\u002F2017-GI-Tutorial-Musik\u002F2017_MuellerWeissBalke_GI_DeepLearningMIR.pdf)  \n- [WWW 2018 Challenge: Learning to Recognize Musical Genre](https:\u002F\u002Fwww.crowdai.org\u002Fchallenges\u002Fwww-2018-challenge-learning-to-recognize-musical-genre)  \n- [Awesome Deep Learning](https:\u002F\u002Fgithub.com\u002FChristosChristofidis\u002Fawesome-deep-learning)  \n- [AINewsFeed](https:\u002F\u002Ftwitter.com\u002FAINewsFeed\u002Fstatus\u002F897832912351105025)  \n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)\n\n## 许可证（License）\n\n您可以在 MIT 许可证条款下自由复制、修改和分发 ***Deep Learning for Music（DL4M）***，并需注明来源。详情请参阅 LICENSE 文件。  \n本项目使用了其他项目，请参考以下项目以获取相应的许可证信息：\n\n- [Readme checklist](https:\u002F\u002Fgithub.com\u002Fddbeck\u002Freadme-checklist) - 用于构建通用 Readme  \n- [Pylint](https:\u002F\u002Fwww.pylint.org\u002F) - 用于清理 Python 代码  \n- [Numpy](http:\u002F\u002Fwww.numpy.org\u002F) - 用于管理 Python 数据结构  \n- [Matplotlib](https:\u002F\u002Fmatplotlib.org\u002F) - 用于绘制图表  \n- [Bibtexparser](https:\u002F\u002Fgithub.com\u002Fsciunto-org\u002Fpython-bibtexparser) - 用于处理 BibTeX 条目  \n\n[返回顶部](https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music#deep-learning-for-music-dl4m-)","# awesome-deep-learning-music 快速上手指南\n\n## 环境准备  \n- **系统要求**：Python 3.7+，Linux\u002FmacOS\u002FWindows 10+  \n- **前置依赖**：  \n  - Git（用于克隆仓库）  \n  - pip（用于安装依赖）  \n- **国内镜像推荐**：  \n  ```bash\n  pip config set global.index-url https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n  ```\n\n---\n\n## 安装步骤  \n1. **克隆仓库**  \n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music.git\n   cd awesome-deep-learning-music\n   ```\n\n2. **安装依赖（如需运行代码示例）**  \n   如果项目包含代码文件（如 `main.py`），可运行：  \n   ```bash\n   pip install -r requirements.txt --no-cache-dir\n   ```\n\n---\n\n## 基本使用  \n1. **查看论文摘要**  \n   直接打开 `DL4M summary` 中的 `.tsv` 或 `.bib` 文件，浏览论文标题、链接及代码地址。  \n\n2. **运行基础示例（假设存在代码文件）**  \n   如果包含可执行代码，示例如下：  \n   ```bash\n   python example_script.py --config configs\u002Fdemo.yaml\n   ```\n\n3. **统计与可视化（如需）**  \n   若包含统计脚本，可运行：  \n   ```bash\n   python stats_generator.py --output fig\u002Fstatistics.png\n   ```\n\n---\n\n> ⚠️ 本项目为论文资源整理仓库，核心功能为查阅学术资料。实际代码需参考文中提供的 GitHub 链接。","音乐科技初创公司的一名研发工程师正在开发AI作曲工具，需要快速了解深度学习在音乐生成领域的最新研究进展和技术方案。\n\n### 没有 awesome-deep-learning-music 时\n- 需要手动在arXiv、Google Scholar等平台搜索\"deep learning music generation\"，每天耗费2小时仍难以覆盖所有相关文献\n- 遇到1995年提出的源识别算法与2023年的Transformer变体难以对比，研究演进脉络不清晰\n- 找到的论文中仅30%提供可复现的代码仓库，且代码质量参差不齐\n- 面对\"Music Information Retrieval\"等跨学科术语时，需要额外查阅领域专有名词解释\n- 无法判断哪些研究已被后续工作改进，存在重复研究风险\n\n### 使用 awesome-deep-learning-music 后\n- 通过按年份\u002F任务分类的表格，30分钟内即可掌握从1988年神经网络建模到2023年扩散模型的完整发展脉络\n- 每篇条目附带论文摘要、代码链接和关键创新点说明，可直接定位到2021年提出的MusicLM等里程碑工作\n- 代码仓库标注了\"PyTorch实现\"或\"Colab可运行\"等标签，优先选择验证过的高质量实现方案\n- 术语表解释了\"Monophonic Source Identification\"等专业概念，降低跨学科理解门槛\n- 通过引用关系图谱发现某篇2018年论文已被2022年研究改进，避免重复开发相似方案\n\n这个工具将音乐领域深度学习研究的检索效率提升了70%，使工程师能将80%精力集中在技术验证而非文献筛选上，显著加速了AI作曲产品的原型开发周期。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fybayle_awesome-deep-learning-music_4b61993a.png","ybayle","Yann Bayle","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fybayle_f92a04c2.jpg","CTO & co-founder @reefpulse | PhD in AI applied to Signal Processing","Reef Pulse","France",null,"reef_pulse","http:\u002F\u002Fyannbayle.fr","https:\u002F\u002Fgithub.com\u002Fybayle",[86,90],{"name":87,"color":88,"percentage":89},"TeX","#3D6117",84.2,{"name":91,"color":92,"percentage":93},"Python","#3572A5",15.8,2957,341,"2026-03-31T08:12:04","MIT",1,"未说明",{"notes":101,"python":99,"dependencies":102},"该项目为论文与代码资源汇总清单，本身无具体运行环境需求。实际使用需参考各条目对应的代码仓库文档",[],[55,13,54],[105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124],"awesome","awesome-list","unicorns","list","lists","resources","deeplearning","deep-learning","deep-neural-networks","neural-network","neural-networks","music","music-information-retrieval","audio","audio-processing","article","music-genre-classification","bib","machine-learning","research",8,"2026-03-27T02:49:30.150509","2026-04-06T05:44:15.900386",[129,134,139,144,149,154],{"id":130,"question_zh":131,"answer_zh":132,"source_url":133},1790,"如何按类别或任务筛选论文列表？","可以通过项目中的 `dl4m.tsv` 文件进行筛选，该文件支持自定义过滤条件。同时，可以参考 `tasks.md` 文件中的任务分类进行排序（例如：音频标签、生成模型等）。具体操作详见：https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music\u002Fblob\u002Fmaster\u002Fdl4m.tsv 和 https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music\u002Fblob\u002Fmaster\u002Ftasks.md","https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music\u002Fissues\u002F19",{"id":135,"question_zh":136,"answer_zh":137,"source_url":138},1791,"如何为项目贡献资源或论文链接？","请遵循贡献指南（CONTRIBUTING.md），将资源链接添加到 ReadMe 或引用已发表的科学论文。具体步骤详见：https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music\u002Fblob\u002Fmaster\u002FCONTRIBUTING.md","https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music\u002Fissues\u002F23",{"id":140,"question_zh":141,"answer_zh":142,"source_url":143},1792,"如何获取 Million Song Dataset (MSD) 的音频数据？","7digital.com 可能已不再提供完整数据集。建议通过 ISRC 或 MBID 使用流媒体服务的 API 获取 30 秒音频片段。","https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music\u002Fissues\u002F16",{"id":145,"question_zh":146,"answer_zh":147,"source_url":148},1793,"如何为项目贡献 Logo 设计？","提交设计提案后，维护者会确认并提供文件下载链接。例如，用户 Mirza Zulfan 提交的 Logo 被采纳后，可通过 Google Drive 下载完整文件：https:\u002F\u002Fdrive.google.com\u002Fdrive\u002Ffolders\u002F1Z2F-ALlz_UzS5VveeH4X_n5vCqQQ2Nlt","https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music\u002Fissues\u002F9",{"id":150,"question_zh":151,"answer_zh":152,"source_url":153},1794,"如何修复 README 中论文链接指向错误的问题？","维护者已修复该问题，确保第二列链接指向代码仓库而非论文原文（如 arXiv、IEEE）。若发现类似问题，可提交 Issue 报告。","https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music\u002Fissues\u002F1",{"id":155,"question_zh":156,"answer_zh":157,"source_url":158},1795,"如何推荐非深度学习领域的相关书籍？","虽然项目聚焦深度学习，但用户可提交书籍链接作为补充资源。例如，Bregman 的《Auditory Scene Analysis》被提及为必读材料，但需维护者评估是否纳入项目。","https:\u002F\u002Fgithub.com\u002Fybayle\u002Fawesome-deep-learning-music\u002Fissues\u002F10",[]]