Auditory-perceptual Parameters as Predictors of Voice Acoustic Measures

Duy Duong Nguyen; Catherine Madill

doi:10.1016/j.jvoice.2023.02.030

Auditory-perceptual Parameters as Predictors of Voice Acoustic Measures

J Voice. 2023 Mar 30:S0892-1997(23)00088-7. doi: 10.1016/j.jvoice.2023.02.030. Online ahead of print.

Authors

Duy Duong Nguyen¹, Catherine Madill²

Affiliations

¹ Voice Research Laboratory, Sydney School of Health Sciences, Faculty of Medicine and Health, The University of Sydney, Sydney, Australia.
² Voice Research Laboratory, Sydney School of Health Sciences, Faculty of Medicine and Health, The University of Sydney, Sydney, Australia. Electronic address: duong.nguyen@sydney.edu.au.

PMID: 37003863
DOI: 10.1016/j.jvoice.2023.02.030

Abstract

Background: Much research has examined the relationship between perceptual and acoustic measures. However, little is known about the prediction values of perceptual measures on an acoustic parameter.

Aims: This study utilized simulated and disordered voice samples to investigate the prediction values of breathiness, roughness, and strain ratings on the selection of some time-based and spectral-based measures of voice quality.

Method: This study retrospectively analysed two sets of precollected data. The experimental data had been collected from nine trained speakers manipulating false vocal fold activity, true vocal fold mass, and larynx height. The voice-disordered data had been extracted from a clinical database for 68 patients with muscle tension voice disorders (MTVD). Both data sets had been perceptually rated for breathiness, roughness, and strain. Voice samples (prolonged vowel /ɑ/ and Rainbow Passage readings) had undergone acoustic analysis using Praat for harmonics-to-noise ratio (HNR) and the program "Analysis of Dysphonia in Speech and Voice" (ADSV) for cepstral peak prominence (CPP), Cepstral/Spectral Index of Dysphonia (CSID), and Low/High spectral ratio (L/H ratio). Perceptual parameters were regressed against these acoustic measures to test their prediction values.

Results: Reliability data showed satisfactory intra- and inter-reliability of perceptual ratings for both data sets. Breathiness significantly predicted CPP (both vocal tasks) and CSID (Rainbow Passage) in experimental data and predicted all the acoustic measures in MTVD data. Roughness significantly predicted HNR, CPP, and CSID in experimental data, and CPP (Rainbow Passage) and CSID (both vocal tasks) in MTVD data. Strain (both vocal tasks) significantly predicted L/H ratio in both data sets.

Conclusions: Breathiness ratings predicted selection of HNR, CPP and CSID; roughness ratings predicted selection of CPP and CSID, and strain ratings predicted L/H ratio.

Keywords: Acoustic analysis; Laryngeal manipulation; Muscle tension voice disorder; Perceptual analysis; Vocal fold; Voice quality.