From TaigiTube to TaigiSpeech: Developing Taiwanese AI for Language Learning and Home Care Assistance
Invited Talk, Stanford University, Stanford, CA, USA
Talks
Game-Time: Evaluating Temporal Dynamics in Spoken Language Models
Conference Oral, ICASSP 2026, Barcelona, Spain
Slides: Game-Time: Evaluating Temporal Dynamics in Spoken Language Models
Towards Better Dynamics in Full-Duplex Spoken Language Models
Invited Talk, UT Austin, Texas, US
Slides: Towards Better Dynamics in Full-Duplex Spoken Language Models
Related Survey: Speech-Trident
This talk starts from our survey paper: “On the Landscape of Spoken Language Models” (TMLR 2025) to introduce spoken language models (SLMs) and the development of full-duplex models that can listen and speak simultaneously. It then covers two contributions: (1) the Game-Time Benchmark (ICASSP 2026), which evaluates temporal dynamics in SLMs such as reaction timing, tempo adherence, and silence management, and (2) Full-Duplex-Bench-v2, a multi-turn evaluation framework with an automated examiner for assessing full-duplex SLMs.
ICASSP 2024 Tutorial: Parameter-Efficient and Prompt Learning for Speech and Language Foundation Models
Tutorial, ICASSP 2024, Seoul, Korea
Presented by: Dr. Huck Yang, Dr. Pin-Yu Chen, Prof. Hung-yi Lee, Kai-Wei Chang, Cheng-Han Chiang
Slides: Speech Language Models: Prompting and Parameter Efficient Learning
Related Survey: Speech-Trident
ICASSP 2023 Tutorial: Parameter‑Efficient Learning for Speech and Language Processing: Adapters, Prompts, and Reprogramming
Tutorial, ICASSP 2023, Rhodes Island, Greece
Presented by: Dr. Huck Yang, Dr. Pin-Yu Chen, Prof. Hung-yi Lee, Kai-Wei Chang, Cheng-Han Chiang
Slides: Parameter-Efficient Learning for Speech Processing
Related Survey: Speech-Prompts-Adapters
Speech Foundation Models
Course, Machine Learning 2023, Taipei, Taiwan
Slides: Speech Foundation Models
Video: Part 1 Part 2
Introduction to ChatGPT
Course, Lingustics 2023, Taipei, Taiwan
Slides: Introduction to ChatGPT