Speech Recognition: Increasing Efficiency of Support Vector Machines

TL;DR

This paper explores improving the efficiency of support vector machines for biometric speech recognition by integrating dimensionality reduction techniques and real-time implementation, enhancing robustness and accuracy.

Contribution

It introduces a biometric system combining SVMs and LDA with MFCCs, optimized for real-time performance and improved robustness.

Findings

Good pattern recognition with multimodal biometric system

Effective dimensionality reduction enhances SVM performance

Real-time implementation demonstrated using SignalWAVE

Abstract

With the advancement of communication and security technologies, it has become crucial to have robustness of embedded biometric systems. This paper presents the realization of such technologies which demands reliable and error-free biometric identity verification systems. High dimensional patterns are not permitted due to eigen-decomposition in high dimensional feature space and degeneration of scattering matrices in small size sample. Generalization, dimensionality reduction and maximizing the margins are controlled by minimizing weight vectors. Results show good pattern by multimodal biometric system proposed in this paper. This paper is aimed at investigating a biometric identity system using Support Vector Machines(SVMs) and Lindear Discriminant Analysis(LDA) with MFCCs and implementing such system in real-time using SignalWAVE.