Assessing Deception by Voice Analysis Part I: The CVSA (Corrected Copy)
AbstractDevices that allegedly can detect lying from “analysis” of aperson’s speech are proliferating. Their presence is creating problems for thecourts, as well as for criminal justice and intelligence agencies. But, canassessments of this type actually provide valid information about deceptivebehaviors even though past research suggests their ability to do so is suspect?As stated, this report will review prior research, provide information about alaboratory experiment, and analyze recent field research. The experiment was alarge, well-controlled, laboratory study of the National Institute of TruthVerification’s (NITV) Computer Voice Stress Analyzer (CVSA). It employed speechsamples of individuals who systematically varied normal with intenselydeceptive and stressed speech. To create the latter, they had to hold verystrong views about some issue and were required to make sharply derogatorystatements about them while believing that they would be observed by colleaguesand friends. A double-blind evaluation by two teams – one trained/certified byNITV; the other made up of NITV senior examiners – was conducted. The resultsdemonstrated that the CVSA system operated only at about chance levels. Thisfinding is consistent with those reported by other investigators; it isconfirmed by field research.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).