Speaker Identification Using a Nonlinear Speech Model and ANN

摘要

This paper introduces a nonlinear speech model for improved speaker identification. We modelled the speaker identity using Reconstructed Phase Space (RPS) of the speech signal and the Phase Space Point Distribution (PSPD) parameters. The PSPD parameters are extracted from five vowels uttered by different speakers. The speaker identification experiments are conducted based on the PSPD parameters using Feed Forward Multi Layer Perceptron (FFMLP). Overall performance of the Mel-frequency cepstral baseline system is compared with the proposed composite classifier system using both cepstral and PSPD features across ten different speakers. The experimental results indicate that the accuracy of the phase space approach by itself is below that of MFCC features and further it shows that the proposed approach in which PSPD features when used with MFCC, pitch and first formant frequency offers reasonable improvement in speaker identification accuracy of the system