I'm a post-doctoral associate at MIT in the Spoken Language Systems group of the Computer Science and Artificial Intelligence Laboratory under the supervision of Jim Glass.
My main research interest is in machine learning and its application to speech processing. I'm currently studying distant speech recognition from a domain adaptation perspective, and how linguistic properties emerge from weakly supervised end-to-end models. During my PhD, I've worked on segmental models, discriminative training, and end-to-end training.
I received my PhD degree from Toyota Technological Institute at Chicago in 2017 under the advisement of Karen Livescu. I joined the Probabilistic Transcription team led by Mark Hasegawa-Johnson in the 2015 Jelinek Summer Workshop. I was an intern at MERL with Shinji Watanabe in 2013.
I received my MS degree in EE from National Taiwan University in 2010 under the advisement of Lin-Shan Lee. I got my BS degree in CS from National Taiwan University in 2007.
You can reach me at