Haitong Zhang received a Master's degree in Speech and Language Processing from the University of Edinburgh in 2017. In 2019, he joined Netease Games AI Lab as a Senior AI researcher. He has a broad academic interest, including speech processing and speech synthesis. He is continuously contributing to the international speech community by publishing papers at the top peer-review conferences.
Selected Peer-review publications:
1. Zhang, H., & Lin, Y. (2020). Unsupervised Learning for Sequence-to-Sequence Text-to-Speech for Low-Resource Languages}}. Proc. Interspeech 2020, 3161-3165.
2. Zhan, H., Zhang, H., Ou, W., & Lin, Y. (2021). Improve Cross-Lingual Text-To-Speech Synthesis on Monolingual Corpora with Pitch Contour Information. In Interspeech (pp. 1599-1603).
3. Zhang, H., & Lin, Y. (2022, May). Improve few-shot voice cloning using multi-modal learning. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 8317-8321). IEEE.
4. Xiao, R., Zhang, H., & Lin, Y. (2022, May). DGC-vector: A new speaker embedding for zero-shot voice conversion. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 6547-6551). IEEE.
Presenting: