Several papers accepted by TASLP, ICASSP 2024, SLT 2024, and other international conferences; developed the large-scale speech dataset Emilia; contributed to multiple projects on neural vocoders; one of the main contributors to the Amphion open-source toolkit.
Research Experience
Currently working as an Audio Engineer at Spellbrush, collaborating with Professors Zhizheng Wu and Lauri Juvela, and closely working with Xueyao Zhang, Junan Zhang, and Chaoren Wang.
Education
Visiting Scholar at Aalto University in Professor Lauri Juvela's lab since September 2024; Research Assistant in Professor Zhizheng Wu's lab at CUHKSZ since October 2022.
Background
Audio Engineer with research interests in audio, speech, and music generation, audio-visual generation, and digital audio effects. Co-founder of Amphion, an open-source toolkit for Audio, Music, and Speech Generation.
Miscellany
The team is broadly interested in Transgender Voice Therapy and is currently collaborating with local hospitals, seeking trans volunteers for their project.