Speaker Identification of the Electronically Disguised Voices

Abstract

Listen

Translate article

Voice is said to be unique for every individual and can be used for the identification. Significant intravariation in Speech samples can be seen with the changes in the physical and mental conditions. Analysisof disguised voice samples is challenging to the Forensic Speaker Identification Expert. Changes inthe voice samples can be done by physical constriction and also with the technologicalinterventions.Speech processing softwares which are freely available and can be used to change voice samples.These softwares add some background variations along with the alterin the frequency distribution inthe voice. This paper focuses on the examination of the voice samples which are processed by a freelyavailable android application which changes the female voice samples to that of male. The examinationwas done on the OT- Expert 6.0. The Examination of the voices was done by the Aural-Acousticsmethod. For the examination of the voice samples on acoustics parameters such as fundamentalfrequency(F0) and Formant Frequencies (F1, F2, F3, F4) for 5 vowels compared with their controlrecordings showed prominent and noteworthy differences. Aural examination parameters such asrelative pauses, background variations, and linguistic features such as delivery of speech, specificpronunciations for words remained similar.Some specific formant frequencies for 5 vowels combinedwith auditory parameters especially the degradation of background of the audio for suspecting a caseof electronically disguised voice and then compared it with a possible list of suspects for speakeridentification. Therefore, based on some specific aural-acoustics features electronically disguisedvoices can be identified amongst the suspected voice samples.