Music Generation Resources

Papers

1. HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
2. Robust Speech Recognition via Large-Scale Weak Supervision
3. Enabling factorized piano music modeling and generation with the MAESTRO Dataset
4. RAVE: A variational autoencoder for fast and high-quality neural audio synthesis
5. Long-form music generation with latent diffusion
6. Do Music Generation Models Encode Music Theory?
7. Multi-Track MusicLDM: Towards Versatile Music Generation with Latent Diffusion Model
8. Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuning
9. Simple and Controllable Music Generation
10. WaveGlow: A Flow-based Generative Network for Speech Synthesis
11. HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
12. Improving Controllability and Editability for Pretrained Text-to-Music Generation Models

Projects

1. OpenAI Whisper
2. Waveglow)
3. MusicLM
4. Riffusion
5. Magenta
6. Audiocraft

Other Tools

1. The MAESTRO Dataset
2. Wave2Midi2Wave