About me

🚀 [2024.01.19] New Blog Post: ESPnet Hackathon 2023✨

Hello! My name is Hsiu-Hsuan Wang, and I am an undergraduate student at National Taiwan University. I will join the Graduate Institute of Electrical Engineering (Computer Science group) to pursue my my Master’s degree. I am fortunate to have Prof. Hung-Yi Lee as my advisor for my Master’s degree.

My undergraduate research projects involved weakly-supervised learning, supervised by Prof. Hsuan-Tien Lin, and speech dialogue modeling, supervised by Prof. Hung-Yi Lee.

Publications

[1] Hsiu-Hsuan Wang^*, W Lin^*, H Lin. CLCIFAR: CIFAR-derived benchmark datasets with human annotated complementary labels

[2] X Chang, B Yan, K Choi, J Jung, Y Lu, S Maiti, R Sharma, J Shi, J Tian, S Watanabe, Y Fujita, T Maekaku, P Guo, Y Cheng, P Denisov, K Saijo, Hsiu-Hsuan Wang. Exploring speech recognition, translation, and understanding with discrete speech units: A comparative study

[3] J Shi, W Chen, D Berrebbi, Hsiu-Hsuan Wang, W Huang, E Hu, H Chuang, X Chang, Y Tang, S Li, A Mohamed, H Lee, S Watanabe. Findings of the 2023 ML-Superb Challenge: Pre-Training And Evaluation Over More Languages And Beyond

[4] H Wu, H Chung, Y Lin, Y Wu, X Chen, Y Pai, Hsiu-Hsuan Wang, K Chang, A Liu, H Lee. Codec-SUPERB: An In-Depth Analysis of Sound Codec Models

[5] I Kang, Hsiu-Hsuan Wang, C Kuan, H Chung, T Hsu, K Chang, P Chen, C Wang, A Lee, H Gong, H Lee. Voxcentum: Spoken Language Identification for 100+ Languages Expanded to 100+ Hours

[6] I fu, Hsiu-Hsuan Wang, H Lee. Investigating the Effects of Large-Scale Pseudo-Stereo Data and Different Speech Foundation Model on Dialogue Generative Spoken Language Model

^* for equal contribution.