MedSpeak: A Knowledge Graph-Aided ASR Error Correction Framework for Spoken Medical QA
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913061183422464 |
|---|---|
| author | Song, Yutong Shrestha, Shiva Lyu, Chenhan Khatibi, Elahe Zhang, Pengfei Xu, Honghui Dutt, Nikil Rahmani, Amir |
| author_facet | Song, Yutong Shrestha, Shiva Lyu, Chenhan Khatibi, Elahe Zhang, Pengfei Xu, Honghui Dutt, Nikil Rahmani, Amir |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00981 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MedSpeak: A Knowledge Graph-Aided ASR Error Correction Framework for Spoken Medical QA Song, Yutong Shrestha, Shiva Lyu, Chenhan Khatibi, Elahe Zhang, Pengfei Xu, Honghui Dutt, Nikil Rahmani, Amir Computation and Language Artificial Intelligence 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. |
| title | MedSpeak: A Knowledge Graph-Aided ASR Error Correction Framework for Spoken Medical QA |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2602.00981 |