一个全面的波兰医学语音数据集,用于增强自动医学语音
Andrzej Czyżewski1, Sebastian Cygert1, Karolina Marciniuk1
1Gdańsk University of Technology, Multimedia Systems Department, Faculty of Electronics, Telecommunications and Informatics,, Gdańsk, Poland.
Scientific data
|August 16, 2025
概括
我们介绍了波兰医学语音数据集ADMEDVOICE. 使用这些数据微调模型显著提高了医疗语音识别的准确性,减少了文字错误率 (WER).
科学领域:
- 语音技术 语言技术
- 医疗信息学 医疗信息学
- 计算语言学 计算语言学
背景情况:
- 预训练的模型提供了强大的零射击能力,但医疗语音识别等专业领域需要量身定制的数据集.
- 现有的资源可能无法充分捕捉医学词汇的细微差别和现实世界的声学条件.
研究的目的:
- 介绍ADMEDVOICE,一个新的波兰医疗语音数据集,旨在改善医疗语音识别.
- 提供包括原始录音,匿名数据和合成数据在内的综合资源,以促进研究和开发.
主要方法:
- 收集了近15个小时的波兰医疗语音数据,来自28名在各种,包括噪音,条件下.
- 创建了匿名和合成 (文本到语音) 版本,将数据集扩展到83个小时以上和5万个样本.
- 评估了Whisper模型,并对其与ADMEDVOICE数据集及其增强版本进行了微调.
主要成果:
- 基线的Whisper模型在测试组中实现了24.03%的文字错误率 (WER).
- 精细调整以人类记录减少了WER到15.47%.
- 纳入匿名和合成数据进一步降低了WER,达到13.91%.
结论:
- ADMEDVOICE数据集显著提高了医学语音识别性能.
- 开源数据集,微调模型和代码促进了该领域的进一步进步.
- 现实,匿名和合成数据的组合为模型训练提供了一个强大的方法.
更多相关视频
相关概念视频
01:26Methods of Documentation II: POMR
1.1K
The Problem-Oriented Medical Record (POMR) revolutionized medical record-keeping by introducing a systematic approach focusing on the patient's problems rather than merely listing symptoms. Dr. Lawrence Weed's introduction of this method in the 1960s marked a significant advancement in medical documentation. The POMR framework consists of four key components: the database, problem list, plan of care, and progress notes.
1.1K
01:24Data Reporting and Recording
4.9K
Reporting and recording are crucial in data documentation. The timely, thorough, and accurate documentation of facts is essential when recording patient data. Failure to record findings during an assessment or interpretation of a problem will result in loss of information and make the patient document unreliable. The reader is left with general impressions if the information is not specific. A recording is documenting data of the individual's health information in a traceable, secure, and...
4.9K