AI People Wiki

Builders & open source

Yi Ren

Leads the foundation video model research team, HeyGen

  • Leads the foundation video model research team, HeyGen12

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

At a glance

Current role
Leads the foundation video model research team
Company
HeyGen
Sector
Company
Work listed
2
Honors
2
Sources cited
7
Profile reviewed

Career

Yi Ren earned a master's degree in computer science at Zhejiang University advised by Zhou Zhao, a frequent co-author, and interned in the machine learning group at Microsoft Research Asia from August 2018 to February 2019. Ren has collaborated closely with Xu Tan, Tao Qin and Tie-Yan Liu of Microsoft Research Asia.1

Ren joined TikTok as a speech research scientist in January 2023 and now works at HeyGen, leading its foundation video model research team, with a focus on large generative models for video and speech. In 2021 Ren was among the young scholars who founded the MLNLP community for machine learning and NLP researchers, and serves as one of its committee chairs.12

Research

Ren's research covers speech synthesis, neural machine translation and automatic music generation. Ren was first author of FastSpeech (2019), a fast, robust and controllable non-autoregressive text-to-speech model that Ren's homepage describes as deployed in the Microsoft Azure TTS service, and of FastSpeech 2 (2020), which trains directly on ground-truth targets instead of a teacher model's output.134

Ren co-authored DiffSinger (2021), which synthesizes singing voices with a shallow diffusion mechanism, was first author of PortaSpeech (2021), a portable generative text-to-speech model, and co-authored Make-An-Audio (2023), a text-to-audio model built on prompt-enhanced diffusion.567

Work and contributions

  • FastSpeech 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 Published research

    First author of FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (ICLR 2021).41

Timeline

  1. Began an internship in the machine learning group at Microsoft Research Asia, lasting until February 2019.1
  2. First author of "FastSpeech - Fast, Robust and Controllable Text to Speech".3
  3. Received the Baidu Scholarship and joined the ByteDance Scholars Program.1
  4. First author of FastSpeech 2, a fast and high-quality end-to-end text-to-speech model.4
  5. Co-authored DiffSinger, on singing voice synthesis via a shallow diffusion mechanism.5
  6. First author of PortaSpeech, a portable and high-quality generative text-to-speech model.6
  7. Joined TikTok as a speech research scientist.1
  8. Co-authored Make-An-Audio, text-to-audio generation with prompt-enhanced diffusion models.7

Other documented roles

Roles the sources document that are not confirmed as current.

Honors and recognition

  • Baidu Scholarship · Baidu, 20201
  • ByteDance Scholars Program · ByteDance, 20201

Where they work

  • Jonathan ShenSpeech and audio · Image, video, and 3D generation
  • Heiga ZenSpeech and audio · Image, video, and 3D generation
  • Jade CopetImage, video, and 3D generation · Speech and audio
  • Neil ZeghidourSpeech and audio · Image, video, and 3D generation
  • Wei-Ning HsuSpeech and audio · Image, video, and 3D generation
  • Ju-Chieh ChouSpeech and audio · Image, video, and 3D generation
  • Xu TanSpeech and audio · Image, video, and 3D generation
  • Alexandre DéfossezSpeech and audio · Image, video, and 3D generation
  • Sanyuan ChenSpeech and audio · Image, video, and 3D generation
  • RJ Skerry-RyanSpeech and audio · Image, video, and 3D generation

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

7 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026

  1. Yi Ren — homepageYi Ren · Official page · accessed Oct 21, 2026
  2. RayeRen (Yi Ren) on GitHub (company HeyGen)GitHub · Official page · accessed Oct 21, 2026
  3. FastSpeech: Fast, Robust and Controllable Text to Speech (arXiv 1905.09263)arXiv · Paper · published May 22, 2019 · accessed Oct 21, 2026
  4. FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (arXiv 2006.04558)arXiv · Paper · published Jun 8, 2020 · accessed Oct 21, 2026
  5. DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (arXiv 2105.02446)arXiv · Paper · published May 6, 2021 · accessed Oct 21, 2026
  6. PortaSpeech: Portable and High-Quality Generative Text-to-Speech (arXiv 2109.15166)arXiv · Paper · published Sep 30, 2021 · accessed Oct 21, 2026
  7. Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models (arXiv 2301.12661)arXiv · Paper · published Jan 30, 2023 · accessed Oct 21, 2026