Screening Voice Disorders: Acoustic Voice Quality Index, Cepstral Peak Prominence, and Machine Learning

被引：0

作者：

Yousef, Ahmed M. ^{[1
,2
,3
]}

Castillo-Allendes, Adrian ^{[3
,4
]}

Berardi, Mark L. ^{[3
]}

Codino, Juliana ^{[5
]}

Rubin, Adam D. ^{[5
]}

Hunter, Eric J. ^{[3
]}

机构：

[1] Massachusetts Gen Hosp, Ctr Laryngeal Surg & Voice Rehabil, Boston, MA 02114 USA

[2] Harvard Med Sch, Dept Surg, Boston, MA 02115 USA

[3] Univ Iowa, Dept Commun Sci & Disorders, Iowa City, IA 52242 USA

[4] Michigan State Univ, Dept Commun Sci & Disorders, E Lansing, MI USA

[5] Lakeshore Profess Voice Ctr, Lakeshore Ear Nose & Throat Ctr, St Clair Shores, MI USA

来源：

FOLIA PHONIATRICA ET LOGOPAEDICA | 2025年

基金：

美国国家卫生研究院;

关键词：

Voice disorders; Machine learning; Speech acoustics; Acoustic Voice Quality Index; Cepstral Peak Prominence; DYSPHONIA SEVERITY; SPEECH; VALIDATION; PITCH;

D O I：

10.1159/000544852

中图分类号：

R36 [病理学]; R76 [耳鼻咽喉科学];

学科分类号：

100104 ; 100213 ;

摘要：

Introduction: The Acoustic Voice Quality Index (AVQI) and Smoothed Cepstral Peak Prominence (CPPs) have been reported to effectively support the assessment of voice quality in persons seeking voice care across many languages. This study aimed to evaluate the diagnostic accuracy of these two measures in detecting voice disorders in American English speakers, comparing their performance to machine learning (ML) models. Methods: This retrospective study included a cohort of 187 participants: 138 patients with clinically diagnosed voice disorders and 49 vocally healthy individuals. Each participant completed two voicing tasks: sustaining [a:] vowel and producing a running speech sample, which were then concatenated. These samples were analyzed using VOXplot software for AVQI-3 (version 03.01) and CPPs. Additionally, four ML models (random forest, k-nearest neighbors, support vector machine, and decision tree) were trained for comparison. The diagnostic accuracy of the two measures and models was assessed using various evaluation metrics, including receiver operating characteristic curve and Youden Index. Results: A cutoff score of 1.54 for the AVQI-3 (with 55% sensitivity and 80% specificity) and 14.35 dB for CPPs (with 65% sensitivity and 78% specificity) were identified for detecting voice disorders. Compared to an average ML sensitivity of 89% and specificity of 55%, CPPs offered a better balance between sensitivity and specificity, outperforming AVQI-3 and nearly matching the average ML performance. Conclusions: ML shows great potential for supporting voice disorder diagnostics, especially as models become more generalizable and easier to interpret. However, current tools like AVQI-3 and CPPs remain more practical and accessible for clinical use in evaluating voice quality than commonly implemented models. CPPs, in particular, offers distinct advantages for identifying voice disorders, making it a recommended and feasible choice for clinics with limited resources.

引用

页数：15