The Accuracy of Auditors' and Layered Voice Analysis (LVA) Operators' Judgments of Truth and Deception During Police Questioning*

Abstract

The purpose of this study was to determine if auditors could identify truthful and deceptive persons in a sample (n = 74) of audio recordings used to assess the effectiveness of layered voice analysis (LVA). The LVA employs an automated algorithm to detect deception, but it was not effective here. There were 31 truthful and 43 deceptive persons in the sample and two LVA operators averaged 48% correct decisions on truth-tellers and 25% on deceivers. Subsequent to the LVA analysis the recordings were audited by three interviewers, each independently rendering a decision of truthful or deceptive and indicating their confidence. Auditors' judgments averaged 68% correct decisions on truth-tellers and 71% on deceivers. Auditors' detection rates, generally, exceeded chance and there was significantly (p < 0.05) greater confidence on correct than incorrect judgments of deceivers but not on truth-tellers. These results suggest that the success reported for LVA analysis may be due to operator's judgment.

Subjective Cues to Deception/Honesty in a High Stakes Situation: An Exploratory Approach

“…Furthermore, the vocal cues are particularly interesting, as for decades efforts have been made to develop voice analysis software to detect deception, using measures such as fundamental frequency, jitter, shimmer, and intensity. However, previous attempts to use measures of vocal characteristics as indicators of deception have generally been without success (see, for example, Giddens et al, 2013;Horvath, McCloughlan, Weatherman & Slowik, 2013). In contrast, the present results suggest that subjective impressions of vocal characteristics may capture an aspect of deceptive behaviour which it has not been possible to measure more objectively.…”

A megtévesztés tipológiája – összefoglaló tanulmány

“…Az elemzés folyhat azonnali "online" és utólagos "offline" módban is. A hangelemzéssel kapcsolatos vizsgálatok eredményei nem mindig egyértelműek (Adler, 2009;Hansberger, Hollien, & Martin, 2009), azonban azt is fontos kiemelni, hogy mint minden szakértői rendszer, ez is hozzáértő szakmai kézben működik a legjobban (Horvath, McCloughan, Weatherman, & Slowik, 2013).…”

Sexe, mensonge et personnalité : les paroles et le regard des machiavéliques, des psychopathes et des narcissiques que vous côtoyez

“…D'autre part, l'analyse vocale a été fortement critiquée sur sa plausibilité car lors d'une tâche de détection du mensonge elle ne donne pas de résultats supérieurs au hasard (Harnsberger, Hollien, Martin, & Hollien, 2009). Par ailleurs, un tel matériel n'a pas la même efficacité suivant la personne qui l'utilise (Horvath, McCloughan, Weatherman, & Slowik, 2013). Nous avons donc choisi de ne pas utiliser de matériel spécifique dans notre étude ce qui, par conséquent, nous a permis de montrer que des changements dans le comportement peuvent être trouvés en l'absence de matériel spécifique lorsqu'il est question de mensonge.…”