I am a Ph.D. student at MIT CSAIL working with Dr. James Glass in the Spoken Language Systems Group. I develop machine learning (especially deep learning) algorithms for natural language and speech processing.

I received a B.S. in Computer Science from National Taiwan University in 2016. When I was an undergrad, I worked with Prof. Hsuan-Tien Lin on active learning, multi-label classification, and cost-sensitive classification. I also worked with Prof. Lin-Shan Lee and Prof. Hung-Yi Lee on acoustic word embeddings, spoken term detection, and question answering.

Projects

Project

Unsupervised Speech Processing

All humans process vast quantities of unannotated speech and manage to learn phonetic inventories, word boundaries, etc., and can use these abilities to acquire new word. Why can't ASR technology have similar capabilities? Our goal in this research project is to build speech technology using unannotated speech corpora.
Jim Glass

Groups