Paper “Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning” accepted to InterSpeech 2024; Paper “On the Evaluation of Speech Foundation Models for Spoken Language Understanding” accepted to Findings of ACL 2024; Paper “What Do Self-Supervised Speech Models Know about Words” accepted to TACL 2024; Paper “Toward Joint Language Modeling for Speech Units and Text” accepted to Findings of EMNLP 2023; Paper “Few-shot SLU via Joint Speech-Text Models” accepted to ASRU 2023 and received the Best Student Paper Award; FastSpeech 2 open-source project got over 1.5k stars on GitHub.
Research Experience
Interned at Amazon Alexa TTS Research, FAIR (AI at Meta), and NVIDIA.
Education
Currently a 3rd-year Ph.D. student at Toyota Technological Institute at Chicago (TTIC), working with Karen Livescu. Previously, earned a Master’s degree in Computer Science from National Taiwan University (NTU), where he worked with Lin-shan Lee and Hung-yi Lee at the Speech Processing Lab.
Background
Research interests encompass speech and natural language processing technologies, focusing on speech language models, speech generation, and self-supervised speech representations.
Miscellany
Sports enthusiast and amateur athlete, captained the baseball varsity team of NTU during undergraduate years. Interested in tennis, hiking, scuba diving, swimming, badminton, and training. Completed his first marathon in 2022, aiming to break the 3:10 mark.