Saved in:
Bibliographic Details
Main Authors: Zhou, Shilin, Li, Zhenghua
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.12252
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911060600029184
author Zhou, Shilin
Li, Zhenghua
author_facet Zhou, Shilin
Li, Zhenghua
contents While end-to-end Automatic Speech Recognition (ASR) models have shown impressive performance in transcribing general speech, they often struggle to accurately recognize contextually relevant keywords, such as proper nouns or user-specific entities. Previous approaches have explored leveraging keyword dictionaries in the textual modality to improve keyword recognition, either through token-level fusion that guides token-by-token generation or phrase-level fusion that enables direct copying of keyword phrases. However, these methods operate at different granularities and have their own limitations. In this paper, we propose a novel multi-grained fusion approach that jointly leverages the strengths of both token-level and phrase-level fusion with Large Language Models (LLMs). Our approach incorporates a late-fusion strategy that elegantly combines ASR's acoustic information with LLM's rich contextual knowledge, balancing fine-grained token precision with holistic phrase-level understanding. Experiments on Chinese and English datasets demonstrate that our approach achieves state-of-the-art performance on keyword-related metrics while preserving high accuracy on non-keyword text. Ablation studies further confirm that the token-level and phrase-level components both contribute significantly to the performance gains, complementing each other in our joint multi-grained framework. The code and models will be publicly available at https://github.com/.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12252
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Contextual ASR via Multi-grained Fusion with Large Language Models
Zhou, Shilin
Li, Zhenghua
Computation and Language
Artificial Intelligence
While end-to-end Automatic Speech Recognition (ASR) models have shown impressive performance in transcribing general speech, they often struggle to accurately recognize contextually relevant keywords, such as proper nouns or user-specific entities. Previous approaches have explored leveraging keyword dictionaries in the textual modality to improve keyword recognition, either through token-level fusion that guides token-by-token generation or phrase-level fusion that enables direct copying of keyword phrases. However, these methods operate at different granularities and have their own limitations. In this paper, we propose a novel multi-grained fusion approach that jointly leverages the strengths of both token-level and phrase-level fusion with Large Language Models (LLMs). Our approach incorporates a late-fusion strategy that elegantly combines ASR's acoustic information with LLM's rich contextual knowledge, balancing fine-grained token precision with holistic phrase-level understanding. Experiments on Chinese and English datasets demonstrate that our approach achieves state-of-the-art performance on keyword-related metrics while preserving high accuracy on non-keyword text. Ablation studies further confirm that the token-level and phrase-level components both contribute significantly to the performance gains, complementing each other in our joint multi-grained framework. The code and models will be publicly available at https://github.com/.
title Improving Contextual ASR via Multi-grained Fusion with Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2507.12252