I am currently a PhD student at Language Technologies Institute of School of Computer Science at Carnegie Mellon University, advised by Dr. Shinji Watanabe. In 2019-2020, I was a PhD student in CLSP at Johns Hopkins University.
You can find my Curriculum Vitae here.
My research focuses on machine learning and its applications in speech processing. I am interested in the Cocktail Party Problem, aiming at building an end-to-end speech recognition system for speech mixtures of multiple sources.
- Speech recognition for single-speaker or multi-speaker
- Speech separation
- Speech translation