Ho-Lam Chung

DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering

Abdel-rahman Mohamed, Hung-yi Lee, Shang-Wen Li, 2022, INTERSPEECH.

Bridging Speech and Textual Pre-Trained Models With Unsupervised ASR

Leibny Paola García-Perera, Hung-yi Lee, Shinji Watanabe, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

ML-SUPERB: Multilingual Speech Universal PERformance Benchmark

Abdel-rahman Mohamed, Hung-yi Lee, Shinji Watanabe, 2023, ArXiv.

Improving Controllability of Educational Question Generation by Keyword Provision pdf

Ho-Lam Chung, Ying-Hong Chan, Yao-Chung Fan, 2021, ArXiv.

T5lephone: Bridging Speech and Text Self-Supervised Models for Spoken Language Understanding Via Phoneme Level T5

Hung-yi Lee, Yu Tsao, Chan-Jan Hsu, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

DUAL: Textless Spoken Question Answering with Speech Discrete Unit Adaptive Learning

Abdel-rahman Mohamed, Hung-yi Lee, Shang-Wen Li, 2022 .

A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies. pdf

Yao-Chung Fan, Ying-Hong Chan, Ho-Lam Chung, 2020, FINDINGS.

Towards General-Purpose Text-Instruction-Guided Voice Conversion

Kai-Wei Chang, Shuo-yiin Chang, Ho-Lam Chung, 2023, 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).