Acoustic Discrimination of Pathological Voice

TLDR

The study examined whether acoustic measures can distinguish normal from pathological voices. Researchers extracted nine acoustic features from sustained vowels and continuous speech of 53 normal and 175 pathological speakers, then used linear discriminant analysis and ROC curves to evaluate classification performance. Individual vowel‑based measures outperformed continuous‑speech measures, but combining features improved accuracy, yielding comparable results for both speech types.

Abstract

We investigated the ability of acoustic measures to discriminate between normal and pathological talkers. Two groups of measures were compared: (a) those extracted from sustained vowels and (b) those based on continuous speech samples. Nine acoustic measures, which include fundamental frequency and amplitude perturbation measures, long term average spectral measures, and glottal noise measures were extracted from both sustained vowel and continuous speech samples. Our experiments were performed on a published database of 53 normal talkers and 175 talkers with a pathological voice. The classification performance of the nine acoustic measures was quantified using linear discriminant analysis and receiver operating characteristic (ROC) curve analysis. When individual measures were considered in isolation, classification was more accurate for measures extracted from sustained vowels than for those based on continuous speech samples. Classification accuracy improved when combinations of acoustic parameters were considered. For such combinations of measures, classification results were comparable for measures extracted from continuous speech samples and for those based on sustained vowels.