Robust speech recognition using evolutionary class-dependent LDA

Authors:
Hossein Moeinzadeh;M-Mehdi Mohammadi;Ahmad Akbari;Babak Nasersharif
Affiliations:
Research center of Information Technology, Department of Computer Engineering Iran University of Science and Technology, Tehra, Tehran, Iran;Research center of Information Technology, Department of Computer Engineering Iran University of Science and Technology, Tehra, Tehran, Iran;Research center of Information Technology, Department of Computer Engineering Iran University of Science and Technology, Tehra, Tehran, Iran;Department of Computer Engineering, Faculty of Engineering University of Guilan, Rasht, Iran, Guilan, Iran
Venue:
Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers
Year:
2009

Citing 2
Cited 3

Introduction to Evolutionary Computing

Introduction to Evolutionary Computing
An improved LDA approach

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Effect of noise-in-speech on MFCC parameters

SSIP '09/MIV'09 Proceedings of the 9th WSEAS international conference on signal, speech and image processing, and 9th WSEAS international conference on Multimedia, internet & video technologies
Improving linear discriminant analysis with artificial immune system-based evolutionary algorithms

Information Sciences: an International Journal
New class-dependent feature transformation for intrusion detection systems

Security and Communication Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Linear Discriminant Analysis (LDA) is a feature selection method in speech recognition. LDA finds transformations that maximizes the between-class scatter and minimizes within-class scatter. This transformation can be obtained in a class-dependent or class independent manner. In this paper, we propose a method to improve LDA and also we use it instead of DCT in MFCC extraction. This transformation matrix is computed through three evolutionary methods (GA, HS, and PSO) to optimize class-dependent LDA transformation matrix for robust MFCC extraction. For this purpose, we first use logarithm of clean speech Mel filter bank energies (LMFE) of each class to define within-class scatter for each class and between-class scatter for over all classes. Next, class-dependent transformation matrix is utilized in place of DCT in MFCC feature extraction. The experimental results show that the proposed speech recognition and optimization methods using class-dependent LDA, achieves a significant isolated word recognition rate on Aurora2 database.