临床语音转录中的与口音相关的错误和基于LLM的补救措施
Yasaman Fatapour1, Jamil S Samaan2, Nicholas P Tatonetti3,4,5,6
1Department of Computational Biomedicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
NPJ digital medicine
|March 2, 2026
概括
像WhisperX这样的AI转录工具在非母语英语的人群中显示出更高的错误. 将WhisperX与GPT-4o结合起来,可以显著减少这些与口音相关的错误,提高临床文档的准确性.
科学领域:
- 医疗信息学 医疗信息学
- 人工智能的人工智能
- 语音识别 语音识别 语言识别
背景情况:
- 准确的临床文档对于患者安全和护理质量至关重要.
- 由人工智能驱动的自动语音识别 (ASR) 提供了简化文档的潜力.
- 跨不同口音的ASR表现的变化带来了转录风险.
研究的目的:
- 评估ASR工具 (Whisper,WhisperX) 对英语母语和非母语英语使用者的临床语音的性能.
- 评估GPT-4o后处理在减轻与口音相关的转录错误方面的有效性.
主要方法:
- 在来自母语和非母语英语使用者的记录临床音频上测试Whisper和WhisperX.
- 分析转录错误率,特别关注与口音相关的不准确性.
- 实施和评估一个链接的ASR-GPT模型 (WhisperX-GPT) 来纠错错误.
主要成果:
- 与母语相比,非母语英语使用者的Whisper和WhisperX的错误率显著更高.
- 使用GPT-4o的后处理转录大大提高了准确性,恢复了由于口音而丢失的信息.
- 组合的WhisperX-GPT方法显示了明显减少了口音特定的转录错误.
结论:
- 需要进一步开发ASR工具,以解决跨语言背景的绩效差异.
- 链式人工智能模型,将ASR与GPT-4o等大型语言模型集成在一起,有望提高临床文档的准确性.
- 威斯珀X-GPT方法提供了一个可行的策略,以减轻AI辅助医学转录中的口音相关错误.
相关概念视频
02:07Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
02:23Master Transcription Regulators
Master transcription regulators are regulatory proteins that are predominantly responsible for regulating the expression of multiple genes. Often these genes work in concert to drive a complex process. Activation of a master transcription regulator can lead to a cascade of transcriptional activation necessary for that outcome. These regulators can directly bind to the regulatory sequences of the various genes involved, or they can indirectly regulate transcription by binding to regulatory...
02:07Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
02:23Master Transcription Regulators
Master transcription regulators are regulatory proteins that are predominantly responsible for regulating the expression of multiple genes. Often these genes work in concert to drive a complex process. Activation of a master transcription regulator can lead to a cascade of transcriptional activation necessary for that outcome. These regulators can directly bind to the regulatory sequences of the various genes involved, or they can indirectly regulate transcription by binding to regulatory...
01:12Types of Errors: Detection and Minimization
Error is the deviation of the obtained result from the true, expected value or the estimated central value. Errors are expressed in absolute or relative terms.
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...
01:21Larynx
The human larynx, often referred to as the voice box, is an intricate organ located in the neck. It serves as a pathway for air to enter the lungs during respiration and is an essential component of voice production.
Anatomy of the Larynx
The larynx consists of various components, including cartilage, muscles, and vocal cords. Its structure includes three large unpaired cartilages—the thyroid, cricoid, and epiglottis—and three smaller paired cartilages—the arytenoids, corniculates, and...
Anatomy of the Larynx
The larynx consists of various components, including cartilage, muscles, and vocal cords. Its structure includes three large unpaired cartilages—the thyroid, cricoid, and epiglottis—and three smaller paired cartilages—the arytenoids, corniculates, and...