解奉龙

解奉龙 Feng-Long Xie

Team leader of audio intelligence

Xiaohongshu

Biography

Feng-Long Xie is the audio intelligence team leader of Xiaohongshu where he engages in research and product development in speech, music and audio intelligence. From 2018 to 2021, he was a senior researcher responsible for transferring speech synthesis technology from research to several products at WeChat, Tencent. Prior to that he worked at Microsoft Research Asia from 2012 to 2018 conduting fundamental research on speech synthesis and recognition. His research interests include speech synthesis and recognition, music information retrieval,music generation and audio signal processing.

Interests
  • Speech Synthesis and Recognition
  • Music Analysis and Generation
  • Computational Linguistics
Education
  • Joint-PhD in Computer Science, 2014-2019

    Harbin Institute of Technology, Microsoft Research Asia

  • Msc in Computer Science, 2012-2014

    Harbin Institute of Technology, Microsoft Research Asia

  • BSc in Computer Science, 2008-2012

    Harbin Institute of Technology

Experience

 
 
 
 
 
Xiaohongshu
Team Leader of Audio Intelligence
Xiaohongshu
October 2021 – Present Beijing
Research and product development in speech, music and audio intelligence
 
 
 
 
 
Wechat, Tencent
Senior Researcher
Wechat, Tencent
October 2018 – October 2021 Beijing
Transferring speech synthesis technology from research to several products at WeChat
 
 
 
 
 
Microsoft Research Asia
Intern
Microsoft Research Asia
January 2012 – October 2018 Beijing
Conduting fundamental research on speech synthesis and recognition

Recent Publications

Quickly discover more publications on my Google scholar.
(2023). MSMC-TTS: Multi-Stage Multi-Codebook VQ-VAE Based Neural TTS. IEEE TASLP.

PDF Cite DOI