以下の論文がINTERSPEECH 2025で採択されました。

AC/DC: LLM-based Audio Comprehension via Dialogue Continuation
Yusuke Fujita, Tomoya Mizumoto, Atsushi Kojima, Lianbo Liu, Yui Sudo

Is Synthetic Data Truly Effective for Training Speech Language Models?
Tomoya Mizumoto, Atsushi Kojima, Yusuke Fujita, Lianbo Liu, Yui Sudo

OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
Yui Sudo, Yusuke Fujita, Atsushi Kojima, Tomoya Mizumoto, Lianbo Liu