Yi Ren
First author of FastSpeech and FastSpeech 2; former MSRA intern; leads video model research at HeyGen
Yi Ren works at HeyGen, where Ren leads the foundation video model research team, and previously joined TikTok as a speech research scientist in 2023. Ren's research covers speech synthesis, neural machine translation, and automatic music generation, and Ren collaborated closely with Xu Tan, Tao Qin, and Tie-Yan Liu of Microsoft Research Asia, where Ren interned in the machine learning group in 2018 and 2019. Ren is first author of FastSpeech, which Ren's homepage describes as deployed in the Microsoft Azure TTS service, and of FastSpeech 2; Ren also co-authored the DiffSinger singing voice synthesis paper.1234
Work
FastSpeech (external site: arxiv.org)Published research
First author of FastSpeech: Fast, Robust and Controllable Text to Speech (NeurIPS 2019), with Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu, and Yangjun Ruan; Ren's homepage says FastSpeech was deployed in the Microsoft Azure TTS service.31
FastSpeech 2 (external site: arxiv.org)Published research
First author of FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (ICLR 2021).41
Other documented roles
Roles the sources document but that are not confirmed as current.
- Speech research scientist (joined January 2023), TikTok1
- Intern (August 2018 to February 2019), Microsoft Research Asia (machine learning group)1
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.