Title: Pitch-based cepstral features for gender classification in noisy environments

Authors: Pawan Kumar; Mahesh Chandra

Addresses: Department of ECE, Birla Institute of Technology, Mesra, Ranchi 835215, India ' Department of ECE, Birla Institute of Technology, Mesra, Ranchi 835215, India

Abstract: Pitch based cepstral features are proposed for a novel gender classification system. A clean and noisy database of 100 speakers, 59 males and 41 females has been used for performing the experiments. Training and testing was performed using Gaussian Mixture Models (GMM) in clean and noisy environments. The proposed, Pitch Based Linear Prediction Cepstral Coefficients (PLPCC) and Pitch Based Mel Frequency Cepstral Coefficients (PMFCC) has shown a maximum of 12.12% and 15.62% increment in performance over Linear Prediction Cepstral Coefficients (LPCC) and Mel Frequency Cepstral Coefficients (MFCC) respectively.

Keywords: autocorrelation; Gaussian mixture models; pitch-based cepstral features; linear prediction cepstral coefficients; pitch-based mel frequency cepstral coefficients; gender classification; males; females; noisy environments.

DOI: 10.1504/IJSISE.2013.054792

International Journal of Signal and Imaging Systems Engineering, 2013 Vol.6 No.3, pp.138 - 142

Received: 19 Apr 2011
Accepted: 04 Aug 2011

Published online: 13 Sep 2013 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article