Saved in:
Bibliographic Details
Main Authors: Kong, YuXiang, Hou, JunFeng, Tang, Jian, Zhu, Bingqing, Zhang, Jicheng, Xue, Shaofei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.21828
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911339286364160
author Kong, YuXiang
Hou, JunFeng
Tang, Jian
Zhu, Bingqing
Zhang, Jicheng
Xue, Shaofei
author_facet Kong, YuXiang
Hou, JunFeng
Tang, Jian
Zhu, Bingqing
Zhang, Jicheng
Xue, Shaofei
contents Large language model (LLM)-based automatic speech recognition (ASR) has recently achieved strong performance across diverse tasks, yet contextual biasing for named entities and hotwords under large vocabularies remains challenging. In this work, we propose a scalable two-stage framework that integrates hotword retrieval with LLM-ASR adaptation. First, we extend the Global-Local Contrastive Language-Audio pre-trained model (GLCLAP) to retrieve a compact top-k set of hotword candidates from a large vocabulary via robustness-aware data augmentation and fuzzy matching. Second, we inject the retrieved candidates as textual prompts into an LLM-ASR model and fine-tune it with Generative Rejection-Based Policy Optimization (GRPO), using a task-driven reward that jointly optimizes hotword recognition and overall transcription accuracy. Experiments on hotword-focused test sets show substantial keyword error rate (KER) reductions while maintaining sentence accuracy on general ASR benchmarks, demonstrating the effectiveness of the proposed framework for large-vocabulary contextual biasing.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21828
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Contextual Biasing for LLM-Based ASR with Hotword Retrieval and Reinforcement Learning
Kong, YuXiang
Hou, JunFeng
Tang, Jian
Zhu, Bingqing
Zhang, Jicheng
Xue, Shaofei
Audio and Speech Processing
Large language model (LLM)-based automatic speech recognition (ASR) has recently achieved strong performance across diverse tasks, yet contextual biasing for named entities and hotwords under large vocabularies remains challenging. In this work, we propose a scalable two-stage framework that integrates hotword retrieval with LLM-ASR adaptation. First, we extend the Global-Local Contrastive Language-Audio pre-trained model (GLCLAP) to retrieve a compact top-k set of hotword candidates from a large vocabulary via robustness-aware data augmentation and fuzzy matching. Second, we inject the retrieved candidates as textual prompts into an LLM-ASR model and fine-tune it with Generative Rejection-Based Policy Optimization (GRPO), using a task-driven reward that jointly optimizes hotword recognition and overall transcription accuracy. Experiments on hotword-focused test sets show substantial keyword error rate (KER) reductions while maintaining sentence accuracy on general ASR benchmarks, demonstrating the effectiveness of the proposed framework for large-vocabulary contextual biasing.
title Contextual Biasing for LLM-Based ASR with Hotword Retrieval and Reinforcement Learning
topic Audio and Speech Processing
url https://arxiv.org/abs/2512.21828