Abstract
Background
Automatic speech recognition (ASR) technology is increasingly being used for transcription in clinical contexts. Although there are numerous transcription services using ASR, few studies have compared the word error rate (WER) between different transcription services among different diagnostic groups in a mental health setting. There has also been little research into the types of words ASR transcriptions mistakenly generate or omit.
Objective
This study compared the WER of 3 ASR transcription services (Amazon Transcribe [Amazon.com, Inc], Zoom-Otter AI [Zoom Video Communications, Inc], and Whisper [OpenAI Inc]) in interviews across 2 different clinical categories (controls and participants experiencing a variety of mental health conditions). These ASR transcription services were also compared with a commercial human transcription service, Rev (Rev.Com, Inc). Words that were either included or excluded by the error in the transcripts were systematically analyzed by their Linguistic Inquiry and Word Count categories.
Methods
Participants completed a 1-time research psychiatric interview, which was recorded on a secure server. Transcriptions created by the research team were used as the gold standard from which WER was calculated. The interviewees were categorized into either the control group (n=18) or the mental health condition group (n=47) using the Mini-International Neuropsychiatric Interview. The total sample included 65 participants. Brunner-Munzel tests were used for comparing independent sets, such as the diagnostic groupings, and Wilcoxon signed rank tests were used for correlated samples when comparing the total sample between different transcription services.
Results
There were significant differences between each ASR transcription service’s WER (P<.001). Amazon Transcribe’s output exhibited significantly lower WERs compared with the Zoom-Otter AI’s and Whisper’s ASR. ASR performances did not significantly differ across the 2 different clinical categories within each service (P>.05). A comparison between the human transcription service output from Rev and the best-performing ASR (Amazon Transcribe) demonstrated a significant difference (P<.001), with Rev having a slightly lower median WER (7.6%, IQR 5.4%-11.35 vs 8.9%, IQR 6.9%-11.6%). Heat maps and spider plots were used to visualize the most common errors in Linguistic Inquiry and Word Count categories, which were found to be within 3 overarching categories: Conversation, Cognition, and Function.
Conclusions
Overall, consistent with previous literature, our results suggest that the WER between manual and automated transcription services may be narrowing as ASR services advance. These advances, coupled with decreased cost and time in receiving transcriptions, may make ASR transcriptions a more viable option within health care settings. However, more research is required to determine if errors in specific types of words impact the analysis and usability of these transcriptions, particularly for specific applications and in a variety of populations in terms of clinical diagnosis, literacy level, accent, and cultural origin.
Subject
Psychiatry and Mental health
Reference47 articles.
1. Key substance use and mental health indicators in the United States: results from the 2020 national survey on drug use and healthSubstance Abuse and Mental Health Services Administration20212023-10-11Rockville, MDCenter for Behavioral Health Statistics, Quality, Substance Abuse, and Mental Health Services Administrationhttps://www.samhsa.gov/data/sites/default/files/reports/rpt35325/NSDUHFFRPDFWHTMLFiles2020/2020NSDUHFFR1PDFW102121.pdf
2. Addressing Psychiatry Workforce Needs: Where Are We Now?
3. Behavioral Health Workforce Projections, 2020-2035National Center for Health Workforce Analysis20222023-10-11https://bhw.hrsa.gov/data-research/projecting-health-workforce-supply-demand
4. Growing the Psychiatry Workforce Through Expansion or Creation of Residencies and Fellowships: the Results of a Survey by the AADPRT Workforce Task Force
5. ZechnerKWaibelAMinimizing word error rate in textual summaries of spoken language20001st Meeting of the North American Chapter of the Association for Computational LinguisticsApril 29-May 4, 2000Seattle Washington186193
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献