32-G442 (Stata Center)
77 Massachusetts Avenue
Cambridge, MA, 02139
I am a fourth year PhD student in Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, working with Dr. James Glass in Spoken Language System Group.
I have been collaborating with the Google Brain Team as a PhD intern/student researcher on text-to-speech projects since June 2018. Previously, I also interned at Mistsubishi Electric Research Lab (MERL) in the Summer, 2016, working on speech separation and multi-channel speech recognition.
I received B.S. in Electrical Engineering from National Taiwan University in 2014. As an undergrad researcher, I worked with Prof. Lin-Shan Lee in Speech Processing Lab, and Prof. Hsuan-Tien Lin in Computational Learning Lab.
My current research focuses on unsupervised learning from sequential data, primarily but not limited to speech. Specifically, I am interested in exploring neural variational inference models for learning speech representations.
Previously, I have also worked on speech recognition, community question answering, speech separation, unsupervised spoken term detection, and active learning.
|Oct 14, 2017||Our paper Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data is accepted by NIPS 2017.|
|Aug 31, 2017||Our paper Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation and Automatic Speech Recognition of Arabic Multi-Genre Broadcast Media is accepted by ASRU 2017.|
|Aug 26, 2017||Slides and code for Learning Latent Representations for Speech Generation and Transformation presented in Interspeech 2017 are available now.|
|May 20, 2017||Our paper Learning Latent Representations for Speech Generation and Transformation is accepted by Interspeech 2017. Check here for more details!|