Identification of disguised voices using feature extraction and classification
Lini T Lal, Avani Nath · 2015
Abstract — Voice disguising is the process of altering or changing one‟s own voice to dissemble his or her own identity. It is being widely used for illegal purposes. Voice disguising can have negative impact on many fields that use speaker recognition techniques which includes the field of Forensics, Security systems, etc. The main challenge of speaker recognition is the risk of fraudsters using voice recordings of legitimate speakers. So it is important to be able to identify whether a suspected voice has been impersonated or not. In this paper, we propose an algorithm to identify disguised voices. The Mel Frequency Cepstral Coefficients (MFCC) is one of the most important feature extraction technique, which is required among various kinds of speech applications. Voice disguising modifies the frequency spectrum of a speech signal and MFCC-based features can be used to describe frequency spectral properties. The identification system uses mean values and correlation coefficients of MFCC and its regression coefficients as the acoustic features. Then Support Vector Machine (SVM) classifiers are used to classify original and disguise voices based on the extracted features. Accurate detection of voices that are disguised by various methods was obtained and the performance of the algorithm is phenomenal.