Liang-Hsuan Tseng
Liang-Hsuan Tseng

Liang-Hsuan (Andy) Tseng

曾亮軒

Ph.D. Student · SPML Lab, NTU

I am a second-year Ph.D. student at the Speech Processing and Machine Learning (SPML) Laboratory of National Taiwan University, advised by Prof. Hung-yi Lee.

My research primarily focuses on speech processing and applied machine learning, with particular interests in automatic speech recognition and spoken language modeling. I have developed a subtitle generator system that automatically transcribes lecture recordings for the entire university, significantly improving accessibility in education.

Recently, I have been working on spoken language modeling, with the aim of developing intelligent and high-fidelity speech generative models.

Experience

Deep Learning Intern

MediaTek Research · Taipei, Taiwan

2024 – 2025

Ph.D. Student

Speech Processing and Machine Learning Lab, NTU · Taipei, Taiwan

2022 – present

Research and Development Intern

Center of Teaching and Learning Development, NTU · Taipei, Taiwan

2021 – present

Publications

TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling

TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling

ICLR'26

Liang-Hsuan Tseng, Yi-Chang Chen, Kuan-Yi Lee, Da-Shan Shiu, Hung-yi Lee

REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR

REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR

NeurIPS'24

Liang-Hsuan Tseng, En-Pei Hu, Cheng-Han Chiang, Yuan Tseng, Hung-yi Lee, Lin-shan Lee, Shao-Hua Sun