Merging the Knowledge of LLMs for Automatic Speech Recognition

2026-09-14

AI Summary

该研究通过模型合并方法将外部语言模型直接集成到基于大语言模型的自动语音识别系统中，以提高目标领域的ASR性能，同时不增加推理时的计算成本。

Abstract

Automatic speech recognition (ASR) systems, trained on paired speech-text data, have been improved by leveraging language models (LMs) trained on text-only data. LM fusion methods such as shallow fusion and density ratio are well-established methods that incorporate external LMs during ASR decoding. However, they incur additional computational costs due to LM inference, which is particularly problematic for recent larger LMs. In this study, we propose incorporating external LMs via model merging. This method integrates the LMs directly into the parameters of an LLM-based ASR model, requiring no additional computational cost at inference. We formulate domain extension and transfer via arithmetic operations on LoRA parameters. Experimental evaluations were conducted for the domain adaptation of LLM-based ASR trained on CSJ and LibriSpeech. We show that our LM merging consistently improved the ASR performance in the target domains, without degrading inference speed or memory footprint.

Problem

• Automatic Speech Recognition
• Language Models
• Computational Costs

Innovation

• model merging
• LoRA parameters
• domain adaptation