Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR

Bingshen Mu; Hexin Liu; Hongfei Xue; Kun Wei; Lei Xie

AAAI 2026technical0 citations

Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR

Bingshen Mu, Hexin Liu, Hongfei Xue, Kun Wei, Lei Xie

Abstract

Automatic Speech Recognition (ASR) aims to convert human speech content into corresponding text. In conversational scenarios, effectively utilizing context can enhance its accuracy. Large Language Models

BibTeX

@inproceedings{aaai2026_hearingmorewithl,
  title = {Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR},
  author = {Bingshen Mu and Hexin Liu and Hongfei Xue and Kun Wei and Lei Xie},
  booktitle = {AAAI 2026},
  year = {2026}
}