I am a Ph.D. candidate in Computer Science at MIT supervised by Dr. James Glass. My research interests lie in the intersection of machine learning and natural language, with special focus on the design and analysis of methods for learning representations from unlabeled/weakly-labeled data. My research goal is to continue to improve the performance of spoken language technology for high-resource languages, and at the same time democratize spoken language technology to low-resource languages.
During my Ph.D., I have interned at Google and Microsoft working on various spoken and written language processing problems within the context of unsupervised or semi-supervised learning. Problems I have worked on include speech synthesis within Google Perception (summer 2018), text summarization (summer 2019) and automatic speech recognition & translation within Google Brain (summer 2021), and spoken language understanding within Microsoft Cognitive Services Research (summer 2020).
I received a S.M. in Computer Science from MIT in 2019 and 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 a wide range of machine learning problems such as active learning, cost-sensitive learning, and multi-label learning. I also worked with Prof. Lin-Shan Lee and Prof. Hung-Yi Lee on audio representation learning and machine reading comprehension.
Feel free to reach out if you have any questions about my work.