Boosting ASR Robustness via Test-Time Reinforcement Learning with Audio-Text Semantic Rewards

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fang, Linghan, Xie, Tianxin, Liu, Li
Format:	Preprint
Published:	2026
Subjects:	Sound Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.05231