Scholar
Kai-Wei Chang
Google Scholar ID: hE_Oq8cAAAAJ
Massachusetts Institute of Technology
Citations & Impact
Citations
634
H-index
14
i10-index
19
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published several papers, including 'On The Landscape of Spoken Language Models: A Comprehensive Survey' and 'SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks'. Served as a tutorial speaker at ICASSP 2023 and ICASSP 2024, organized the Codec SUPERB Challenge at SLT 2024, and served as Poster Session Chair at ICASSP 2025. Also a Meta-reviewer for ASRU 2025 and Program Chair for ROCLING 2025.
Research Experience
- Works in the Spoken Language System (SLS) Group at MIT CSAIL, led by Dr. James Glass. Served as a research scientist intern at Meta’s Reality Labs (June 2023 - Dec. 2023). Collaborated with multiple companies such as Meta, ASUS, and Bonio Inc. on projects related to speech recognition, translation, and pronunciation evaluation systems.
Education
- Graduated from National Taiwan University in 2025 with a Ph.D., advised by Prof. Hung-yi Lee. His dissertation was titled 'Towards a Universal Speech Model: Prompting Speech Language Models for Diverse Speech Processing Tasks'.
Background
- Research interests include speech processing tasks and generative spoken language models. Currently a Postdoctoral Fellow at MIT CSAIL, working on a universal speech model.
Miscellany
- In May 2025, launched TaigiTube, a website that helps people learn Taiwanese through clips from popular Taiwanese dramas. The site attracted attention from major TV stations in Taiwan and Kai-Wei was invited to share the story behind TaigiTube. He also participated in a 40-minute in-depth interview on a BCC radio program.
Co-authors