Sanyuan Chen
Research scientist at Meta FAIR; first author of WavLM and co-first author of VALL-E
- Research Scientist, Meta (FAIR)1
Sanyuan Chen's GitHub profile describes a role as a research scientist at Meta FAIR. Chen's homepage covers earlier work as a research intern in the Natural Language Computing Group at Microsoft Research Asia, focused on language model pre-training for speech and audio processing, where Chen developed pre-trained models including WavLM, VALL-E, and BEATs. Chen is first author of WavLM, a self-supervised pre-training model for full-stack speech processing, and co-first author of the VALL-E paper, Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers.1235
Work
WavLM (external site: arxiv.org)Published research
First author of WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing (2021), a Microsoft paper.342
VALL-E (external site: arxiv.org)Published research
Co-first author, with Chengyi Wang and Yu Wu, of Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers (2023), the VALL-E paper.52
Other documented roles
Roles the sources document but that are not confirmed as current.
- Research Intern, Natural Language Computing Group (from May 2020), Microsoft Research Asia2
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.