Perceptual Evaluation of the Effectiveness of Voice Disguise by Age Modification

TL;DR

This study evaluates how effectively age stereotypes as a voice disguise strategy are perceived and how they influence speaker recognition, revealing gender and age-related differences in perceived age accuracy.

Contribution

It provides a perceptual assessment of age-based voice disguises, highlighting differences in perceived age accuracy across genders and age groups, and fills a gap in understanding their believability.

Findings

Listeners estimated intended old and child voices close to target ages for females.

Male speakers' intended elderly voices were perceived accurately, but children's voices were often misjudged.

Male children's disguised voices were perceived as older than actual, indicating limitations in disguise effectiveness.

Abstract

Voice disguise, purposeful modification of one's speaker identity with the aim of avoiding being identified as oneself, is a low-effort way to fool speaker recognition, whether performed by a human or an automatic speaker verification (ASV) system. We present an evaluation of the effectiveness of age stereotypes as a voice disguise strategy, as a follow up to our recent work where 60 native Finnish speakers attempted to sound like an elderly and like a child. In that study, we presented evidence that both ASV and human observers could easily miss the target speaker but we did not address how believable the presented vocal age stereotypes were; this study serves to fill that gap. The interesting cases would be speakers who succeed in being missed by the ASV system, and which a typical listener cannot detect as being a disguise. We carry out a perceptual test to study the quality of the disguised speech samples. The listening test was carried out both locally and with the help of Amazon's Mechanical Turk (MT) crowd-workers. A total of 91 listeners participated in the test and were instructed to estimate both the speaker's chronological and intended age. The results indicate that age estimations for the intended old and child voices for female speakers were towards the target age groups, while for male speakers, the age estimations corresponded to the direction of the target voice only for elderly voices. In the case of intended child's voice, listeners estimated the age of male speakers to be older than their chronological age for most of the speakers and not the intended target age.