Full list of publications
Here is a link to all of our research publications.
As part of the project, we open source some of the datasets that were used in our research.
A self-attention-based neural network that can generate music with long-term coherence.
- A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
- Learning a Latent Space of Multitrack Measures
- MusicVAE: Creating a palette for musical scores with machine learning.
- Multitrack MusicVAE: Interactively Exploring Musical Styles
A recurrent neural network (RNN) able to construct stroke-based drawings of common objects. The model is trained on thousands of crude human-drawn images representing hundreds of classes.
A powerful new WaveNet-style autoencoder model that conditions an autoregressive decoder on temporal codes learned from the raw audio waveform.
- NSynth: Neural Audio Synthesis
- Making a Neural Synthesizer Instrument
- Generate your own sounds with NSynth
- Using NSynth to win the Outside Hacks Music Hackathon 2017
- Hands on, with NSynth Super