About

I am a first-year PhD student at NUS, supervised by Prof. Wang Ye. My research interests broadly focus on the speech and singing voice related perception and synthesis, such as speech recognition, speech synthesis, singing voice synthesis, and voice conversion. I earned my B.S. from Beijing Forestry University in 2022.

My cv is here. If you would like to reach out to me, my email address is xintongwang9709 at gmail dot com.

Work Experience

National University of Singapore

Research Assistant @ School of Computing (SMC Lab), Singapore, Oct 2023 – Aug 2024

Xiaoice

Also known as 小冰 in Chinese and りんな in Japanese

Speech Synthsis Engineer @ Xiaoice (X·studio), Beijing, Jul 2022 – Oct 2023

Speech Recognition Intern @ Xiaoice (AI Being BU), Beijing, May 2021 – Jul 2022

Publications

Journal Articles

1. Xintong Wang, Chuangang Zhao, "A 2D Convolutional Gating Mechanism for Mandarin Streaming Speech Recognition," Information, 12.4 (2021): 165. PDF

Workshop Articles

1. Xintong Wang, Chang Zeng, Jun Chen, and Chunhui Wang, "Crosssinger: A Cross-Lingual Multi-Singer High-Fidelity Singing Voice Synthesizer Trained on Monolingual Singers." 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Demo PDF

Conference Articles

1. Xintong Wang, Mingqian Shi, and Ye Wang, "Pitch-Aware RNN-T for Mandarin Chinese Mispronunciation Detection and Diagnosis," Interspeech 2024 PDF