This repository serves as a curated, comprehensive survey of state-of-the-art deep learning and AI techniques for music generation. It targets researchers, engineers, and practitioners in music technology and AI, providing a structured overview of key models, architectures, datasets, and applications in both symbolic and audio domains.

How It Works

The repository organizes research by year and domain (symbolic vs. audio), detailing influential neural network architectures like LSTMs, CNNs, VAEs, GANs, Transformers, and Diffusion Models. It links to seminal papers, code repositories, and presentations, tracing the evolution of music generation models from early algorithmic approaches to modern deep learning paradigms.

Quick Start & Requirements

This repository is a curated list of research papers and resources, not a runnable software project. No installation or execution commands are applicable.

Highlighted Details

• Extensive chronological listing of deep learning models for both symbolic music generation (2015-2023) and audio music generation (2017-2023).
• Includes foundational neural network architectures (LSTM, CNN, VAE, GAN, Transformer, Diffusion Models) with links to original papers.
• Features a section on datasets, journals, conferences, authors, research groups, and AI music generation applications.
• Provides links to a PDF version of the README and encourages contributions via pull requests.

Maintenance & Community

Maintained by Carlos Hernández-Oliván. Contributions are welcomed via pull requests.

Licensing & Compatibility

The repository itself contains links to external resources, and the licensing of those individual resources is not specified here. The content is presented for informational purposes.

Limitations & Caveats

The repository is a curated list and does not provide executable code or pre-trained models. The information is primarily focused on research published up to early 2023, with some older foundational work included.