Resources
Resources
Reading group log
Reading list maintained by the research group.
| # | Paper | Authors | Link |
|---|---|---|---|
| 06 | High Fidelity Neural Audio Compression | Défossez, Copet, Synnaeve, Adi | arXiv ↗ (opens in new tab) |
| 05 | SoundStream: An End-to-End Neural Audio Codec | Zeghidour, Luebs, Omran, Skoglund, Tagliasacchi | arXiv ↗ (opens in new tab) |
| 04 | RAVE: A Variational Autoencoder for Fast and High-Quality Neural Audio Synthesis | Caillon, Esling | arXiv ↗ (opens in new tab) |
| 03 | DDSP: Differentiable Digital Signal Processing | Engel, Hantrakul, Gu, Roberts | arXiv ↗ (opens in new tab) |
| 02 | The Bach Doodle: Approachable Music Composition with Machine Learning at Scale | Huang, Hawthorne, Roberts, Dinculescu, Wexler, Hong, Howcroft | arXiv ↗ (opens in new tab) |
| 01 | WaveNet: A Generative Model for Raw Audio | van den Oord, Dieleman, Zen, Simonyan, Vinyals, Graves, Kalchbrenner, Senior, Kavukcuoglu | arXiv ↗ (opens in new tab) |
Starter kit
DAWs & environments
- Ableton Live ↗ (opens in new tab)
Digital audio workstation. Student discount available.
- Max/MSP ↗ (opens in new tab)
Visual patching environment for audio and media. Available in several NYU labs.
- SuperCollider ↗ (opens in new tab)
Code-based synthesis and composition platform. Free, cross-platform.
- Pure Data ↗ (opens in new tab)
Open-source visual patching environment. Runs on most hardware, including Raspberry Pi.
Libraries
- Tone.js ↗ (opens in new tab)
JavaScript framework built on the Web Audio API.
- Web Audio API ↗ (opens in new tab)
Browser-native audio processing and synthesis.
- RAVE ↗ (opens in new tab)
Real-time neural audio synthesis model from IRCAM.
- librosa ↗ (opens in new tab)
Python library for audio and music analysis.