Kai-Wei Chang 張凱爲

Kai-Wei Chang is a Postdoctoral Fellow at MIT CSAIL, working in the Spoken Language System (SLS) Group led by Dr. James Glass. He holds a Ph.D. from National Taiwan University, where he was advised by Prof. Hung-yi Lee. He graduated in 2025, with a dissertation titled “Towards a Universal Speech Model: Prompting Speech Language Models for Diverse Speech Processing Tasks”.

He has 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. He is also a Meta-reviewer for ASRU 2025 and Program Chair for ROCLING 2025. He also gained industry experience as a research scientist intern at Meta’s Reality Labs.

In May 2025, Kai-Wei Chang started TaigiTube 台語水管, a website that helps people learn Taiwanese in a lively, everyday context with clips from popular Taiwanese dramas. Within just three days of its launch, the site attracted the attention of major TV stations in Taiwan, including FTV (Formosa TV), PTS (Public Television Service), and TVBS, which invited Kai-Wei to share the story behind TaigiTube and praised its fresh approach to keeping Taiwanese alive. He also participated in a 40-minute in-depth interview on a BCC radio program, talking about his vision and the journey of building TaigiTube.

Selected Publications

• On The Landscape of Spoken Language Models: A Comprehensive Survey
  Kai-Wei Chang^*, Siddhant Arora^*, Chung-Ming Chien^*, Yifan Peng^*, Haibin Wu^*, Yossi Adi^†, Emmanuel Dupoux^†, Hung-Yi Lee^†, Karen Livescu^†, Shinji Watanabe^†

• SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks
  Kai-Wei Chang, Haibin Wu, Yu-Kai Wang, Yuan-Kuei Wu, Hua Shen, Wei-Cheng Tseng, Iu-thing Kang, Shang-Wen Li, Hung-yi Lee
  IEEE/ACM TASLP Volume 32, 2024

• An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks
  Kai-Wei Chang, Wei-Cheng Tseng, Shang-Wen Li, Hung-yi Lee
  Interspeech 2022

• SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks
  Kai-Wei Chang, Yu-Kai Wang, Hua Shen, Iu-thing Kang, Wei-Cheng Tseng, Shang-Wen Li, Hung-yi Lee
  Preprint

• SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts
  Kai-Wei Chang*, Haibin Wu*, Yuan-Kuei Wu*, Hung-yi Lee
  Preprint

• Prompting and Adapter Tuning For Self-Supervised Encoder-Decoder Speech Model
  Kai-Wei Chang, Ming-Hsin Chen, Yun-Ping Lin, Jing Neng Hsu, Paul Kuo-Ming Huang, Chien-yu Huang, Shang-Wen Li, Hung-yi Lee
  ASRU 2024

• Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks
  Kai-Wei Chang, Ming-Hao Hsu, Shang-Wen Li, Hung-yi Lee
  Interspeech 2024

• Toward degradation-robust voice conversion
  Kai-Wei Chang\*, Chien-yu Huang*, Hung-yi Lee>
  ICASSP 2022

For the full publication list, please refer to my google scholar

Internship

• Meta Reality Labs - Research Scientist Intern June 2023 - Dec. 2023

Industrial Cooperation

• Meta - Data Mining with Seamless Communication Feb. 2022 - Present

• ASUS - Taiwanese Speech Recognition & Translation Nov. 2021 - Present

• Bonio Inc. - Taiwanese Pronounciation Evaluation System Oct. 2021 - June 2022

Conference Tutorials

• ICASSP 2024: Parameter-Efficient and Prompt Learning for Speech and Language Foundation Models
  Chao-Han Huck Yang (Amazon), Pin-Yu Chen (IBM Research), Hung-yi Lee (National Taiwan University),Kai-Wei Chang (National Taiwan University), Cheng-Han Chiang (National Taiwan University)

• ICASSP 2023: Parameter‑Efficient Learning for Speech and Language Processing: Adapters, Prompts, and Reprogramming
  Pin-Yu Chen (IBM Research), Hung-yi Lee (National Taiwan University), Chao-Han Huck Yang (Georgia Institute of Technology), Kai-Wei Chang (National Taiwan University), Cheng-Han Chiang (National Taiwan University)

Teaching Assistant & Leadership

• Machine Learning, 2021 Spring - Head Teaching Assistant Instrutor: Prof. Hung-yi Lee

  Led and coordinated with over 40 teaching assistants and over 1300 students.

• Linear Algebra, 2020 Fall - Head Teaching Assistant Instrutor: Prof. Hung-yi Lee

  Led and coordinated with over 6 teaching assistants and about 130 students.