Comparative Analysis of Speaker Recognition System Based on Voice Activity Detection Technique, MFCC and PLP Features

Due to rapid advancement in technology, speaker recognition systems become more robust and user friendly. The idea is to study and analyse the speech signal based on feature extraction method. This paper compares the performance of Mel-Frequency Cepstral Coefficient (MFCC) and PLP feature extraction with voice activity detection (VAD) technique. Vector Quantisation approach is used for features matching to select the combination which gives highest accuracy.

[1]  Ali Gharsallah,et al.  Speech analysis in search of speakers with MFCC, PLP, Jitter and Shimmer , 2017, 2017 International Conference on Advanced Systems and Electric Technologies (IC_ASET).

[2]  Michele Scarpiniti,et al.  Text Independent Automatic Speaker Recognition System Using Mel-Frequency Cepstrum Coefficient and Gaussian Mixture Models , 2012, J. Information Security.

[3]  H Hermansky,et al.  Perceptual linear predictive (PLP) analysis of speech. , 1990, The Journal of the Acoustical Society of America.

[4]  Karthik Selvan,et al.  Speaker recognition system for security applications , 2013, 2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS).

[5]  S. R. Mahadeva Prasanna,et al.  Foreground Speech Segmentation and Enhancement Using Glottal Closure Instants and Mel Cepstral Coefficients , 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[6]  Mike Brookes,et al.  Voice source cepstrum coefficients for speaker identification , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[7]  Jesper Jensen,et al.  Minimum Mean-Square Error Estimation of Mel-Frequency Cepstral Features–A Theoretically Consistent Approach , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[8]  Moeness G. Amin,et al.  Automatic Data-Driven Frequency-Warped Cepstral Feature Design for Micro-Doppler Classification , 2018, IEEE Transactions on Aerospace and Electronic Systems.

[9]  Jr. J.P. Campbell,et al.  Speaker recognition: a tutorial , 1997, Proc. IEEE.

[10]  Daniel Garcia-Romero,et al.  Linear versus mel frequency cepstral coefficients for speaker recognition , 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.