Profile

Experience

2026.04 – Present: Research Scientist
Shanda Group Corp · Tokyo, Japan
Speech recognition, generation, and grounded speech models
2025.04 – 2026.03: Research Scientist
SB Intuitions, SoftBank · Tokyo, Japan
Speech-to-speech modeling and spoken interaction
2024.10 – 2025.03: Researcher
Kyoto University · Kyoto, Japan
Multi-talker ASR and speaker-aware speech processing
2024.04 – 2024.09: Research Fellow
Kyoto University · Kyoto, Japan
Noise-robust automatic speech recognition
2023.08 – 2023.09: Research Intern
NTT CS Lab · Keihanna, Japan
Deterministic and diffusion speech enhancement, system fusion
2023.01 – 2023.03: Research Intern
Sony R&D · Tokyo, Japan
Diffusion-based speech enhancement

2021 – 2024: Ph.D. in Informatics
Kyoto University, Speech and Audio Processing Lab.
Thesis: Speech Enhancement Using Spectrogram Feature Fusion for Noise Robust Speech Recognition
2018 – 2021: M.Sc. in Computer Science and Technology
Tianjin University
2014 – 2018: B.Sc. in Computer Science and Technology
Southwest Jiaotong University

Organizing: Special Session Organizer, ICASSP 2027: “Speaker Grounding in Speech LLMs: Recognition, Attribution, and Understanding in Multi-Talker Scenes”
Challenge Organizer, ICASSP 2026: “Automatic Song Aesthetics Evaluation Challenge”
Chairing: Session Chair, ICASSP 2026
Reviewing: Journals: IEEE Trans. ASLP, Speech Communication, IEEE Signal Processing Letters
Conferences and workshops: ICASSP, INTERSPEECH, ASRU, SLT, WASPAA, APSIPA ASC, IJCNN
Membership: IEEE Member, ISCA Member