Affiliation:
1. Emory University School of Medicine Atlanta Georgia USA
2. Georgia State University Atlanta Georgia USA
3. Department of Otolaryngology‐Head & Neck Surgery University of Washington School of Medicine Seattle Washington USA
Abstract
AbstractObjectiveThis study seeks to quantify how current speech recognition systems perform on dysphonic input and if they can be improved.Study DesignExperimental machine learning methods based on a retrospective database.SettingSingle academic voice center.MethodsA database of dysphonic speech recordings was created and tested against 3 speech recognition platforms. Platform performance on dysphonic voice input was compared to platform performance on normal voice input. A custom speech recognition model was trained on voice from patients with spasmodic dysphonia or vocal cord paralysis. Custom model performance was compared to base model performance.ResultsAll platforms performed well on normal voice, and 2 platforms performed significantly worse on dysphonic speech. Accuracy metrics on dysphonic speech returned values of 84.55%, 88.57%, and 93.56% for International Business Machines (IBM) Watson, Amazon Transcribe, and Microsoft Azure, respectively. The secondary analysis demonstrated that the lower performance of IBM Watson and Amazon Transcribe was driven by performance on spasmodic dysphonia and vocal fold paralysis. Thus, a custom model was built to increase the accuracy of these pathologies on the Microsoft platform. Overall, the performance of the custom model on dysphonic voices was 96.43% and on normal voices was 97.62%.ConclusionCurrent speech recognition systems generally perform worse on dysphonic speech than on normal speech. We theorize that poor performance is a consequence of a lack of dysphonic voices in each platform's original training dataset. We address this limitation with transfer learning used to increase the performance of these systems on all dysphonic speech.
Subject
Otorhinolaryngology,Surgery
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
1. Augmented Datasheets for Speech Datasets and Ethical Decision-Making;2023 ACM Conference on Fairness, Accountability, and Transparency;2023-06-12