[4N1-GS-7] Vision, speech media processing:

[4N1-GS-7-05] Correction of Speech Recognition Errors using Word Pronunciation Information to Improve Speech Recognition Accuracy in Medical

〇Tasuku Kitade¹, May Phyo Khaing², Masanori Tsujikawa¹, Koji Okabe¹, Ryo Ishii³, Hitoshi Yamamoto¹, Masahiro Kubo¹, Atsuhiro Nakagawa³, Yukio Katori³ (1. NEC Corporation, 2. Human Resocia Co.,Ltd., 3. Tohoku University Hospital)

Keywords:Correction of Speech Recognition Errors, Word Pronunciation, Medical

We are investigating a medical documentation assistant system that aims to improve the efficiency of record and report creation by physicians by automatically generating medical documents from the recognized results of speech. For this system, it is essential that medical terminology is recognized with high accuracy. Difficult to obtain medical data, we propose a method to correct speech recognition errors using word reading information without using it. Specifically, we detect speech recognition errors from the recognition results using a Large Language Model (LLM) and obtain the readings of words identified as recognition errors through morphological analysis. Furthermore, we extract words similar to those readings and finally select the appropriate word from them using the LLM to correct the recognition errors. Evaluation experiments using simulated medical speech recognition results confirmed that the proposed method achieved a 12.9% reduction in errors of medical terms.