CV

Teaching Assistant

11-751 Speech Recognition and Understanding, Carnegie Mellon University

Research Collaborator

WAVLab, Carnegie Mellon University

Building phone foundation model and evaluation benchmark, supervised by Prof. Shinji Watanabe.

Teaching Assistant

11-4/611 Natural Language Processing, Carnegie Mellon University

Graduate Researcher

ChangeLing Lab, Carnegie Mellon University

Researching speech processing with a phonetic/phonological focus, supervised by Prof. David R. Mortensen.

Research Assistant

Department of Neurology Neurological Institute, Taipei Veterans General Hospital

Applied computer vision techniques to clinical seizure recording, including action recognition and privacy protection.

Undergraduate Researcher

Intelligent Agents Lab, National Taiwan University

Handled data processing and model evaluation for Traditional Chinese LLM development, supervised by Prof. Jane Yung-Jen Hsu.

Teaching Assistant / DNS Team Member

Network Administration and System Administration Team, National Taiwan University

Research Assistant

Biomedical Acoustic Signal Processing Lab, Academia Sinica

Research in audio-visual speech enhancement and speaker diarization, supervised by Dr. Yu Tsao and Dr. Jen-Cheng Hou.

M.S.

Carnegie Mellon University

Intelligent Information Systems (ML / NLP)

B.Sc.

National Taiwan University

Computer Science and Information Engineering

Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages

Interspeech 2025

Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention

ACL 2025

Epileptic Seizure Classification with Patient-Level and Video-Level Contrastive Pretraining

EMBC 2024

Face swapping in seizure videos for patient deidentification

Epilepsy Research

AI-based face transformation in patient seizure videos for privacy protection

MCP: Digital Health

Deep Complex U-Net with Conformer for Audio-Visual Speech Enhancement

AVSEC, Interspeech 2024 Satellite Event

Phonetic Speech Foundation Model

Building speech foundation model supporting phoneme recognition

• Speech Processing
• Phonetics & Phonology

Data Augmentation for Pathological Speech

Investigating voice conversion on cross-lingual dysarthric speech

• Speech Processing
• Atypical Speech

Training Decoder-Only ASR with Long Context

Explored cache retrieval to extend context with limited compute

• Speech Processing
• Efficiency

TAIDE - Trustworthy AI Dialog Engine

A trustworthy generative AI dialogue engine tailored for Taiwan

• LLM Evaluation
• Data Curation

EGO4D Audio-Visual Speaker Diarization Challenge 2023

Applied S3L embeddings and people tracking to egocentric videos

• Multimodal
• Speech Processing