Published multiple papers in conferences such as ICASSP 2025, ASRU 2025, Interspeech 2025, IEEE SLT 2024; Organized events like URGENT 2025 Challenge, Audio Imagination Workshop; Involved in projects like MelodyFlow, FoleyGen, etc.
Research Experience
Senior research scientist at Meta Reality Labs working on generative models for audio, text, and video. Previously, a maintainer of TorchAudio, the official audio library of PyTorch.
Education
PhD student, advised by Michael I Mandel; Undergraduate student, advised by Yan Xu.
Background
Research Interests: Single-channel/multi-channel speech enhancement, generative models, and natural language processing. Recently interested in generative models for music and audio codec.