Title 

Speaker identification of the Electronically Disguised Voices.

Authors 

Palak Aneja, Sumit Kumar Choudhary, Surbhi Mathur

Abstract 

Background: Voice is said to be unique for every individual and can be used for the identification. Significant intra variation in Speech samples can be seen with the changes in the physical and mental conditions. Analysis of disguised voice samples is challenging to the Forensic Speaker Identification Expert. Speech processing softwares which are freely available and can be used to change voice samples. These softwares add some background variations along with the alter in the frequency distribution in the voice. Methodology: This paper focuses on the examination of the voice samples which are processed by a freely available android application which changes the female voice samples to that of male. The examination was done on the OT- Expert 6.0. The Examination of the voices was done by the Aural-Acoustics method. Results: For the examination of the voice samples on acoustics parameters such as fundamental frequency(F0) and Formant Frequencies (F1, F2, F3, F4) for 5 vowels (/?/, /?/, /i/, /I/, /u/) compared with their control recordings showed prominent and noteworthy differences. Aural examination parameters such as relative pauses, background variations, and linguistic features such as delivery of speech, specific pronunciations for words remained similar. Conclusion: Some specific formant frequencies for 5 vowels (/? /, /? /, /i /, /I /, /u/) combined with auditory parameters especially the degradation of background of the audio for suspecting a case of electronically disguised voice and then compared it with a possible list of suspects for speaker identification. Therefore, based on some specific auralacoustics features electronically disguised voices can be identified amongst the suspected voice sample.

 Keywords

Acoustic, Disguise, Forensic, Speaker, Identification.

 DOI