Neil Zeghidour
First author of SoundStream and co-author of AudioLM at Google Research; Audio Research Advisor at Kyutai
Neil Zeghidour is listed as Audio Research Advisor on Kyutai's team page, and Zeghidour's GitHub profile describes AI research at Kyutai. As a research scientist at Google Research, Zeghidour was first author of SoundStream, an end-to-end neural audio codec presented on the Google Research blog in 2021, and a co-author of AudioLM, a language-modeling approach to audio generation presented there in 2022. Zeghidour is also a co-author of the Moshi speech-text foundation model paper from Kyutai.12345678
Work
SoundStream (external site: arxiv.org)Published research
First author of SoundStream: An End-to-End Neural Audio Codec (2021) and co-author of the Google Research blog post introducing it, which credits the work to Zeghidour, Alejandro Luebs, Ahmed Omran, Jan Skoglund, and Marco Tagliasacchi.43
AudioLM (external site: arxiv.org)Published research
Last author of AudioLM: a Language Modeling Approach to Audio Generation (2022) and co-author, with Zalán Borsos, of the Google Research blog post presenting it.65
Moshi (external site: arxiv.org)Published research
Co-author of Moshi: a speech-text foundation model for real-time dialogue (2024), with Alexandre Défossez and other Kyutai researchers.78
Other documented roles
Roles the sources document but that are not confirmed as current.
- Research Scientist, Google Research (blog bylines, 2021 and 2022), Google Research35
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.