Antoine Caillon

Research scientist - deep generative modeling applied to musical signals.

Currently

Research Scientist at Google DeepMind.

PhD Subject

Hierachical temporal learning for multi-instrument and orchestral audio synthesis

Research interests

Neural audio synthesis, real-time implementation of deep generative models, artistic use of artificial intelligence

Education

2020-2023 PhD: Hierachical temporal learning for multi-instrument and orchestral audio synthesis

2018-2019 Master Degree 2 ATIAM

2017-2018 Master Degree 1 Engineering Sciences

2015-2017 Mathematic degree

2012-2014 Sound engineering degree

Previous positions

2022 Google Brain, invited student researcher

2020-2023 IRCAM, PhD student

2019 IRCAM, Software engineer

2019 Technicolor, intern

Publications

2022 SingSong: Generating musical accompaniments from singing

2022 MusicLM: Generating Music From Text

2022 Streamable Neural Audio Synthesis With Non-Causal Convolutions

2021 RAVE: A variational autoencoder for fast and high-quality neural audio synthesis

2020 Timbre latent space: exploration and creative aspects

2020 Diet deep generative audio models with structured lottery

2019 Assisted Sound Sample Generation with Musical Conditioning in Adversarial Auto-Encoders

Projects

2024 MusicFX DJ v2

2022 nn~ : a Max/MSP external for real-time ai audio processing

2021-2022 RAVE: Official implementation

2020 ddsp_pytorch

Artistic collaborations

2024 Jacob Collier

2021-2022 ANIMA TM

2021 Improvisation, apprentissage profond et fusion d’espace latent

2019-2020 Convergence

2019-2020 unknown title

Master class

2022 Neural Audio Synthesis

Neural Audio Synthesis

RAVE + nn~

Teaching

2020-now Internship supervision

2020-2023 Machine learning project

2020-now React Native course