用检索增强生成修复语音识别错误，实时提升准确率。
RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition
- 动态检索音文对与领域词库，补全识别假设
- 融合检索结果后，显著降低语音识别错误率
- 适合需要高精度实时语音识别的场景
本文提出RAG-Boost（ST-ShinozakiLab Task I系统），在MLC-SLM挑战赛（任务I）的基线大语言模型语音识别系统基础上，引入在线检索增强生成（RAG）模块。每个部分识别结果会查询包含音文对和领域术语的向量数据库，将检索到的内容与当前识别假设融合，修正识别错误，再输入大语言模型生成更优输出。该方法实现了对原始系统的有效增强。
原文摘要 · Abstract (English)
In this paper, we propose RAG-Boost (ST-ShinozakiLab Task I system), which enhances the baseline LLM-based ASR system of the MLC-SLM Challenge (task I) with a retrieval-augmented generation (RAG) module on the fly. Each partial ASR hypothesis queries a vector store of audio-text pairs and domain terms, and the retrieved results are fused with the live ASR hypotheses to fix recognition errors. The fused hypotheses are passed to the LLM, yielding improved responses.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。