English(EN) MedSpeak: A Knowledge Graph-Aided ASR Error Correction Framework for Spoken Medical QA

MedSpeak框架通过知识图谱校正ASR错误，改进医学问答

作者 PulseAugur 编辑部 · [1 个来源] · 2026-04-28 04:00

研究人员开发了MedSpeak，一个旨在提高医学领域口语问答系统准确性的新框架。该系统利用医学知识图谱来辅助自动语音识别（ASR）纠正错误，尤其是在处理专门的医学术语时。通过将知识图谱中的语义和语音信息与大型语言模型相结合，MedSpeak提高了转录准确性和最终答案的预测。 AI

影响通过利用知识图谱和LLM改进ASR错误校正，提高了医学问答系统的准确性。

排序理由这是一篇详细介绍特定应用新框架的研究论文。

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 这是一篇详细介绍特定应用新框架的研究论文。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 189 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Yutong Song, Shiva Shrestha, Chenhan Lyu, Elahe Khatibi, Pengfei Zhang, Honghui Xu, Nikil Dutt, Amir Rahmani · 2026-04-28 04:00

MedSpeak：一个知识图谱辅助的语音识别错误纠正框架，用于口语医学问答

arXiv:2602.00981v2 Announce Type: replace Abstract: 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 corr…