Biography
Yusheng Tian is a Lecturer in the Department of Computer Science and Engineering at the Chinese University of Hong Kong (CUHK). She completed her PhD in Electronic Engineering at CUHK, working in the DSP & Speech Technology Lab. Her research has been focused on speech and language processing, particularly assistive technologies for people with speech impairments. Previously, she worked as a speech technology engineer at iFlyTek AI Lab. She also holds an M.Sc. degree in Speech and Language Processing from the University of Edinburgh and a B.Eng. degree in Electrical Engineering from Tsinghua University.
Yusheng Tian, Jingyu Li and Tan Lee: Creating Personalized Synthetic Voices from Articulation Impaired Speech Using Augmented Reconstruction Loss. ICASSP 2024: 11501-11505.
- Yusheng Tian, Wei Liu and Tan Lee: Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data. ASRU 2023: 1-7.
- Yusheng Tian, Guangyan Zhang and Tan Lee: Creating Personalized Synthetic Voices from Post-Glossectomy Speech with Guided Diffusion Models. INTERSPEECH 2023: 4893-4897.
- Yusheng Tian, Jingyu Li and Tan Lee: Transport-Oriented Feature Aggregation for Speaker Embedding Learning. INTERSPEECH 2022: 316-320.