Xu Tan
Research VP of Multimodality at Moonshot AI; formerly Principal Research Manager at Microsoft Research Asia
- Research VP of Multimodality, Moonshot AI1
Xu Tan is Research VP of Multimodality at Moonshot AI (Kimi) and was previously a Principal Research Manager in the Machine Learning Group at Microsoft Research Asia, working on language models, multimodality, and generative AI for video and audio. Tan's homepage lists audio models such as FastSpeech 1 and 2, NaturalSpeech 1, 2, and 3, and Kimi-Audio, along with Muzic, an MIT-licensed Microsoft repository for music understanding and generation whose README lists Tan as a co-author of several of its papers. Tan is first author of the NaturalSpeech paper, which builds an end-to-end text-to-waveform system around a variational autoencoder, and a co-author of FastSpeech and FastSpeech 2.123456
Work
NaturalSpeech (external site: arxiv.org)Published research
First author of NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality (2022), which uses a variational autoencoder for end-to-end text-to-waveform generation.41
FastSpeech and FastSpeech 2 (external site: arxiv.org)Published research
Third author, after Yi Ren and Yangjun Ruan, of FastSpeech (2019), and co-author of FastSpeech 2 (2020); Tan's homepage lists both among the audio models Tan designed.561
Muzic (external site: github.com)Open-source code
Muzic, a project for music understanding and generation started by researchers at Microsoft Research Asia, is published under the MIT license; its README lists Tan as a co-author of several of its papers.31
Other documented roles
Roles the sources document but that are not confirmed as current.
- Principal Research Manager, Microsoft Research Asia (Machine Learning Group)12
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.