Liang-Hsuan Tseng

Introducing Semantics into Speech Encoders

Yizhou Sun, Hung-yi Lee, Shang-Wen Li, 2022, ACL.

Improving Generalizability of Distilled Self-Supervised Speech Processing Models Under Distorted Settings

Fabian Ritter Gutierrez, Hung-yi Lee, Kuan-Po Huang, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models pdf

Hung-yi Lee, Heng-Jui Chang, Liang-Hsuan Tseng, 2021, ArXiv.

Improving Cascaded Unsupervised Speech Translation with Denoising Back-translation

Hung-yi Lee, Shinji Watanabe, Jiatong Shi, 2023, arXiv.org.

Leave No Knowledge Behind During Knowledge Distillation: Towards Practical and Effective Knowledge Distillation for Code-Switching ASR Using Realistic Data

Liang-Hsuan Tseng, Zih-Ching Chen, Wei-Shun Chang, 2024, 2407.10603.