Awesome Deep Learning Music
A curated list of scientific articles, theses, and reports on deep learning applied to music information retrieval and generation.
What is Awesome Deep Learning Music?
Awesome Deep Learning Music is a curated collection of scientific articles, theses, and reports that apply deep learning techniques to music-related tasks. It provides a structured overview of research in music information retrieval, generation, classification, and analysis using neural networks. The repository serves as a reference hub for academics and developers exploring AI in music.
Researchers, graduate students, and developers working in music information retrieval, audio machine learning, or computational musicology who need a curated starting point for literature review or project inspiration.
It aggregates and annotates a wide temporal range of deep learning music papers in one place, saving researchers time from manual literature searches. The inclusion of code links and reproducibility notes adds practical value beyond a simple bibliography.
Overview
List of articles related to deep learning applied to music
Use Cases
Best For
- Finding foundational and state-of-the-art papers on deep learning for music
- Identifying available code implementations for music AI research
- Exploring datasets commonly used in music information retrieval tasks
- Understanding the historical progression of neural networks in music analysis
- Discovering research on specific tasks like music transcription, genre classification, or source separation
- Gathering references for literature reviews or thesis writing in music technology
Not Ideal For
- Developers seeking the latest deep learning models and research papers published after 2021
- Practitioners needing ready-to-use software libraries, APIs, or production tools for music AI applications
- Beginners looking for step-by-step tutorials or hands-on coding examples in music deep learning
- Projects focused on commercial music production or real-time audio processing without academic research overhead
Pros & Cons
Pros
Curates over 160 annotated entries from 1988 to 2021, providing a comprehensive timeline of deep learning advancements in music.
Each entry includes detailed fields like architecture, tasks, datasets, and reproducibility notes, facilitating systematic literature reviews.
Highlights source code links for 47 articles (28%), helping researchers quickly find and assess implementations.
Features a clear contribution guide and acknowledges multiple contributors, encouraging collaborative updates and maintenance.
Cons
The repository is explicitly marked as unmaintained with no updates beyond 2021, missing recent breakthroughs and trends in the field.
Only a minority of entries provide code links, limiting practical utility for developers aiming to replicate or build upon research.
Lacks tutorials, tools, or practical guides, making it less accessible for industry practitioners or those seeking immediate implementation.
Frequently Asked Questions
Related Projects
AI Expert RoadmapRoadmap to becoming an Artificial Intelligence Expert in 2022
Machine Learning for Software Engineers, by Nam VuA complete daily plan for studying to become a machine learning engineer.
Microsoft RecommendersBest Practices on Recommendation Systems
Face recognition with Google's FaceNet deep neural network.Face recognition with deep neural networks.
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.