Cubic Law and MAP Compensation Techniques for Robust Text-Independent Speaker Identification

Automatic speaker recognition is drastically degraded in presence of noise. This paper focuses on the application of the cubic law and histogram mapping for the text-independent speaker recognition task. Our aim of this study is the application of these two methods in the feature extraction stage of the Power-Normalized Cepstral Coefficients (PNCC) and the conventional Mel Frequency Cepstral Coefficients (MFCC) techniques. Recognition results show that the cubic law combined with the histogram mapping improve the recognition rates.

I. Introduction

Speaker identification aims to use the speech signal to identify which of the registered speakers it belongs. Nevertheless, the recognition performance is severely degraded in noisy environments, especially under very low SNR. Robust strategies can be deployed in different stages of processing such as on the pre-processing, on the features extraction, on the classifier system or in the choice of the measure of similarity.