About Me
I am a Ph.D. student in the Department of Technology Management for Innovation at the University of Tokyo, Japan, supervised by Prof. Yutaka Matsuo.
My research focuses on reinforcement learning for audio understanding and reward-guided alignment for audio generation. I am also interested in unified generation of speech and non-speech audio, as well as joint audio–video generation.
Publications
-
NeurIPS -
APSIPA ASC SMC-ITA: Sequential Monte Carlo Inference-Time Alignment for Video-to-Audio Generation
-
Interspeech AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
-
ACL Findings ToolGrad: Efficient Tool-use Dataset Generation with Textual “Gradients”
-
ACM Multimedia Emotionally Situated Text-to-Speech Synthesis in User-Agent Conversation
-
Interspeech GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech
Experience
-
–Present
The University of Tokyo
Ph.D. student in Technology Management for Innovation
-
–
ByteDance
Speech Algorithm Engineer
-
–
The University of Tokyo
Master’s in Electrical Engineering and Information Systems