用医学知识图谱和大模型修正语音识别错误，提升医疗问答准确率
MedSpeak: A Knowledge Graph-Aided ASR Error Correction Framework for Spoken Medical QA
- 结合医学知识图谱的语义与发音信息，修正语音识别错误
- 在医疗问答任务中显著提升术语识别与整体性能
- 适合医疗语音系统研发者及临床辅助诊断技术开发者
依赖自动语音识别（ASR）的语音问答（SQA）系统在识别医学术语时常出现误差。为此，我们提出MedSpeak，一种基于知识图谱的ASR错误修正框架，通过融合医学知识图谱中的语义关系与发音信息，结合大语言模型的推理能力，对噪声文本进行优化，从而提升下游答案预测的准确性。在多个基准测试上的实验结果表明，MedSpeak显著提升了医学术语识别准确率和整体医疗SQA性能，成为当前最先进的医疗SQA解决方案。代码已公开于https://github.com/RainieLLM/MedSpeak。
原文摘要 · Abstract (English)
Spoken question-answering (SQA) systems relying on automatic speech recognition (ASR) often struggle with accurately recognizing medical terminology. To this end, we propose MedSpeak, a novel knowledge graph-aided ASR error correction framework that refines noisy transcripts and improves downstream answer prediction by leveraging both semantic relationships and phonetic information encoded in a medical knowledge graph, together with the reasoning power of LLMs. Comprehensive experimental results on benchmarks demonstrate that MedSpeak significantly improves the accuracy of medical term recognition and overall medical SQA performance, establishing MedSpeak as a state-of-the-art solution for medical SQA. The code is available at https://github.com/RainieLLM/MedSpeak.
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。