← Search

Pengchao Feng

2 accepted papers

2025

Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation

EMNLP 2025

End-to-end speech-to-speech (S2S) dialogue systems have recently garnered increasing research attention for their lower latency and more natural integration of nonverbal cues such as emotion and speaker identity. However, these systems face key challenges, particularly in incorporating external know