I’m a senior research scientist at Meta Reality Labs working on generative models for audio, text, and video. Previously, I was a maintainer of TorchAudio library, the official audio library of PyTorch. Before Meta, I was a PhD student advised by Michael I Mandel and an undergraduate student advised by Yan Xu.

My research interests are single-channel/multi-channel speech enhancement, generative models, and natural language processing. Recently, I’m interested in RL for audio domain but still at the exploration stage.

πŸ”₯ News

  • 2024.12: Β πŸŽ‰πŸŽ‰ One paper has been accepted by ICASSP 2025!
  • 2024.11: Β πŸŽ‰πŸŽ‰ We are organizing the URGENT 2025 Challenge at Interspeech 2025! Join in the challenge if you are interested in speech enhancement!
  • 2024.09: Β πŸŽ‰πŸŽ‰ Check out the demo of our MelodyFlow paper, that can do text-guided music editing and generation on 48kHz sample rate music!
  • 2024.09: Β πŸŽ‰πŸŽ‰ Three papers have been accepted by IEEE SLT 2024!
  • 2024.06: Β πŸŽ‰πŸŽ‰ We are organizing β€œAudio Imagination Workshop” at NeurIPS 2024! We cordially invite you to submit your paper or demo through this link!
  • 2024.05: Β πŸŽ‰πŸŽ‰ We are organizing the URGENT challenge at NeurIPS 2024 Competition track!
  • 2024.04: Β πŸŽ‰πŸŽ‰ Our MMS paper has been accepted by Journal of Machine Learning Research!
  • 2024.02: Β πŸŽ‰πŸŽ‰ Checkout the demo videos and paper of our FoleyGen model!
  • 2023.12: Β πŸŽ‰πŸŽ‰ Five papers have beed accepted by ICASSP 2024!
  • 2023.09: Β πŸŽ‰πŸŽ‰ Our TorchAudio 2.1 paper has been accepted by ASRU 2023!
  • 2023.05: Β πŸŽ‰πŸŽ‰ One paper has been accepted by Interspeech 2023!
  • 2023.02: Β πŸŽ‰πŸŽ‰ Two papers have been accepted by ICASSP 2023!

πŸ“ Publications