Selected Publications

Creating Personalized Synthetic Voices from Articulation Impaired Speech Using Augmented Reconstruction Loss. Yusheng Tian, Jingyu Li and Tan Lee. In ICASSP 2024.

Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data. Yusheng Tian, Wei Liu and Tan Lee. In ASRU 2023.

Convolution-based channel-frequency attention for text-independent speaker verification. Jingyu Li, Yusheng Tian, and Tan Lee. In ICASSP 2023.

Creating Personalized Synthetic Voices from Post-Glossectomy Speech with Guided Diffusion Models. Yusheng Tian, Guangyan Zhang and Tan Lee. In INTERSPEECH 2023.

Transport-Oriented Feature Aggregation for Speaker Embedding Learning. Yusheng Tian, Jingyu Li and Tan Lee. In INTERSPEECH 2022.

Improving End-to-End Spoken Intent Classification with Reptile. Yusheng Tian and Philip John Gorinski. In INTERSPEECH 2020.