Hi, I'm Xinlei Ren（任新蕾）👋

• 🍞 I work for StarMaker and have previously worked for Baidu（百度）and Kuaishou（快手）

• 👨‍🎓 I received my Bachelor's and Master's degrees from Northwestern Polytechnical University（西北工业大学）in 2015 and 2018, respectively

• 📚 My work and research interests cover meeting and entertainment scenarios, and mainly include:

  • speech enhancement: acoustic echo cancellation, single/multi-channel de-noising and de-reverberation
  • audio effect: auto gain control and dynamic range control
  • sound event detection: detecting breath, stress and falsetto of singing, hiss and f0
  • singing evaluation: scoring the users' singing based on pitch, rhythm, skill, enthusiasm and range
  • speech quality assessment: scoring the speech clips
  • speech synthesis: Vall-E, Mega-TTS 2
  • ...

  I am skilled at using techniques based on traditional signal processing and deep neural networks to address these audio problems.

• 🔗 More information about me: https://xinleiren.github.io/