An F-Ratio Based Optimization on Noisy Data for Speaker Recognition Application

Automatic Speaker Recognition (ASR) needs a robust acoustic feature for representation of speaker and an efficient modeling scheme to yield high recognition accuracy even at adverse conditions. This paper presents a noise study of an ASR system using Mel-Frequency Cepstral Coefficients (MFCC) and an Artificial Neural Network (ANN) classifier. Optimization in feature space using Fisher's F-Ratio score is done in order to develop reduced speaker model in no noise (only ambient room noise is present) as well as in several noisy conditions. A new ranking scheme is also proposed in order to stabilize the rank of features in various noise levels by taking Arithmetic Mean of the F-Ratio scores obtained from various levels of Signal to Noise Ratio (SNR). The result is presented for a Text-Dependent ASR system with 25 speaker database.