用大模型增强对话上下文，提升无用户数据场景下的语音识别纠错效果
Contextual ASR Error Handling with LLMs Augmentation for Goal-Oriented Conversational AI
- 基于对话状态和任务上下文，用大模型对语音识别候选句排序
- 在真实用户测试中纠错召回率提升34%，F1提升16%
- 适合缺乏历史数据的智能客服、语音助手等目标导向对话场景
通用自动语音识别（ASR）系统在目标导向对话中表现不佳。现有纠错方法依赖用户历史数据或命名实体。本文提出一种新方法，通过大语言模型结合上下文增强与排序策略，将上下文信息融入纠错过程，分别根据词汇语义相似性对n-best识别结果排序，并依据发音对应关系对上下文进行排序。在家庭维修与烹饪领域的真实用户测试中，该方法使纠错召回率提升34%，F1提升16%，同时保持精度与误报率稳定。用户评分在纠错有效时提高0.8-1分（满分5分），且未因误纠错而下降。
原文摘要 · Abstract (English)
General-purpose automatic speech recognition (ASR) systems do not always perform well in goal-oriented dialogue. Existing ASR correction methods rely on prior user data or named entities. We extend correction to tasks that have no prior user data and exhibit linguistic flexibility such as lexical and syntactic variations. We propose a novel context augmentation with a large language model and a ranking strategy that incorporates contextual information from the dialogue states of a goal-oriented conversational AI and its tasks. Our method ranks (1) n-best ASR hypotheses by their lexical and semantic similarity with context and (2) context by phonetic correspondence with ASR hypotheses. Evaluated in home improvement and cooking domains with real-world users, our method improves recall and F1 of correction by 34% and 16%, respectively, while maintaining precision and false positive rate. Users rated .8-1 point (out of 5) higher when our correction method worked properly, with no decrease due to false positives.
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。