Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Arora, Siddhant, Tian, Jinchuan, Shi, Jiatong, Futami, Hayato, Kashiwagi, Yosuke, Tsunoo, Emiru, Watanabe, Shinji
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.19063