Quantifying the effect of speech pathology on automatic and human speaker verification

TL;DR

This study examines how speech pathology, due to oral cancer surgery, affects automatic and human speaker verification performance, revealing negative impacts and correlations with speech severity, alongside perceptual comparisons.

Contribution

It provides new insights into the impact of speech pathology on speaker verification systems using parallel pre- and post-surgery datasets.

Findings

Pathological speech reduces ASV accuracy

Speech severity correlates with decreased ASV performance

Moderate agreement between perceptual and objective severity scores

Abstract

This study investigates how surgical intervention for speech pathology (specifically, as a result of oral cancer surgery) impacts the performance of an automatic speaker verification (ASV) system. Using two recently collected Dutch datasets with parallel pre and post-surgery audio from the same speaker, NKI-OC-VC and SPOKE, we assess the extent to which speech pathology influences ASV performance, and whether objective/subjective measures of speech severity are correlated with the performance. Finally, we carry out a perceptual study to compare judgements of ASV and human listeners. Our findings reveal that pathological speech negatively affects ASV performance, and the severity of the speech is negatively correlated with the performance. There is a moderate agreement in perceptual and objective scores of speaker similarity and severity, however, we could not clearly establish in the perceptual study, whether the same phenomenon also exists in human perception.