A genetic classification method for speaker recognition

Q. Y. HONG, S. KWONG

Research output: Journal PublicationsJournal Article (refereed)peer-review

32 Citations (Scopus)

Abstract

Gaussian mixture model (GMM) has been widely used for modeling speakers. In speaker identification, one major problem is how to generate a set of GMMs for identification purposes based upon the training data. Due to the hill-climbing characteristic of the maximum likelihood (ML) method, any arbitrary estimate of the initial model parameters will usually lead to a sub-optimal model in practice. To resolve this problem, this paper proposes a hybrid training method based on genetic algorithm (GA). It utilizes the global searching capability of GA and combines the effectiveness of the ML method. Experimental results based on TI46 and TIMIT showed that this hybrid GA could obtain more optimized GMMs and better results than the simple GA and the traditional ML method. © 2004 Elsevier Ltd. All rights reserved.
Original languageEnglish
Pages (from-to)13-19
JournalEngineering Applications of Artificial Intelligence
Volume18
Issue number1
DOIs
Publication statusPublished - Feb 2005
Externally publishedYes

Bibliographical note

This work is supported by City University of Hong Kong Strategic Grant Number 7001488.

Keywords

  • Gaussian mixture model
  • Genetic algorithm
  • Speaker identification

Fingerprint

Dive into the research topics of 'A genetic classification method for speaker recognition'. Together they form a unique fingerprint.

Cite this