PCA/LDA Approach for Text-Independent Speaker Recognition

TL;DR

This paper introduces a PCA/LDA-based method for text-independent speaker recognition that is faster and achieves high accuracy, comparable to traditional methods, using a mixed model approach on the TIMIT dataset.

Contribution

A novel PCA/LDA hybrid approach that improves speed while maintaining competitive accuracy in speaker recognition tasks.

Findings

Achieves up to 100% classification rate on TIMIT dataset

Significantly reduces training and operation time compared to MFCC-GMM methods

Effective with short speech segments of 4-12 seconds

Abstract

Various algorithms for text-independent speaker recognition have been developed through the decades, aiming to improve both accuracy and efficiency. This paper presents a novel PCA/LDA-based approach that is faster than traditional statistical model-based methods and achieves competitive results. First, the performance based on only PCA and only LDA is measured; then a mixed model, taking advantages of both methods, is introduced. A subset of the TIMIT corpus composed of 200 male speakers, is used for enrollment, validation and testing. The best results achieve 100%; 96% and 95% classification rate at population level 50; 100 and 200, using 39-dimensional MFCC features with delta and double delta. These results are based on 12-second text-independent speech for training and 4-second data for test. These are comparable to the conventional MFCC-GMM methods, but require significantly less time to train and operate.