Codebook Design Method for Noise Robust Speaker Identification based on Genetic Algorithm

TL;DR

This paper introduces a genetic algorithm-based method for designing noise-robust codebooks in speaker identification, utilizing Wiener filtering and various speech features to improve accuracy in noisy environments.

Contribution

It proposes a novel codebook design approach using genetic algorithms to enhance noise robustness in speaker identification systems.

Findings

Achieved 79.62% accuracy on NOIZEOUS database.

Compared performance across multiple speech feature extraction methods.

Demonstrated the effectiveness of genetic algorithms in optimizing codebook quality.

Abstract

In this paper, a novel method of designing a codebook for noise robust speaker identification purpose utilizing Genetic Algorithm has been proposed. Wiener filter has been used to remove the background noises from the source speech utterances. Speech features have been extracted using standard speech parameterization method such as LPC, LPCC, RCC, MFCC, (delta)MFCC and (delta)(delta) MFCC. For each of these techniques, the performance of the proposed system has been compared. In this codebook design method, Genetic Algorithm has the capability of getting global optimal result and hence improves the quality of the codebook. Comparing with the NOIZEOUS speech database, the experimental result shows that 79.62 percent accuracy has been achieved.