most citedDuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization

1 citations · 1 across the 10 of their papers we have counts for

collaborators
Showing eess.ASShow all

3 papers · 1 filter

eess.AS2026

Does Translation-Enhanced Speech Encoder Pre-training Affect Speech LLMs?

Tomoya Mizumoto, Yusuke Fujita

Connecting a pre-trained speech encoder to a Large Language Model (LLM) is the standard architecture for building Speech LLMs. However, a structural misalignment exists between the…

eess.AS2026

Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models

Tomoya Mizumoto, Yusuke Fujita, Hao Shi +3

Dialogue systems based on large language models (LLMs) have advanced significantly in recent years. However, dialectal variation remains a major challenge, particularly for systems…

eess.AS2025

AC/DC: LLM-based Audio Comprehension via Dialogue Continuation

Yusuke Fujita, Tomoya Mizumoto, Atsushi Kojima +2

We propose an instruction-following audio comprehension model that leverages the dialogue continuation ability of large language models (LLMs). Instead of directly generating targe…