Contextual Biasing of Named-Entities with Large Language Models

This paper studies contextual biasing with Large Language Models (LLMs), where during second-pass rescoring additional contextual information is provided to a LLM to boost Automatic Speech Recognition (ASR) performance. We propose to leverage prompts for a LLM without fine tuning during rescoring wh...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-09
Hauptverfasser:	Sun, Chuanneng, Ahmed, Zeeshan, Ma, Yingyi, Liu, Zhe, Lucas Kabela, Pang, Yutong, Kalinli, Ozlem
Format:	Artikel
Sprache:	eng
Schlagworte:	Automatic speech recognition Datasets Large language models Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!