Optimal Operators of Hybrid Genetic Algorithm for GMM Parameter Estimation

Author

Zablotskiy, Sergey ; Pitakrat, Teerat ; Zablotskaya, Kseniya ; Minker, Wolfgang

Author_Institution

Dept. of Inf. Technol., Univ. of Ulm, Ulm, Germany

fYear

2011

fDate

25-28 July 2011

Firstpage

61

Lastpage

65

Abstract

A genetic algorithm is an evolutionary algorithm that is widely used for solving global optimization problems. It generates the solution in the form of encoded binary chromosome using operators inspired by a natural evolution process: selection, crossover and mutation. In this paper, a hybrid genetic algorithm is applied to the emission probability estimation task of a continuous Hidden Markov Model which is one of the common optimization problems in speech recognition. Three backbone operators of the genetic algorithm are investigated in order to find the optimal Gaussian parameters that result in the best mixture model.

Keywords

Gaussian processes; evolutionary computation; genetic algorithms; hidden Markov models; parameter estimation; speech recognition; GMM parameter estimation; Gaussian parameters; Hidden Markov Model; binary chromosome; evolutionary algorithm; global optimization problems; hybrid genetic algorithm; optimal operators; probability estimation; speech recognition; Biological cells; Genetic algorithms; Genetics; Hidden Markov models; Optimization; Parameter estimation; Wheels; expectation-maximization; genetic algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Environments (IE), 2011 7th International Conference on

Conference_Location

Nottingham

Print_ISBN

978-1-4577-0830-5

Electronic_ISBN

978-0-7695-4452-6

Type

conf

DOI

10.1109/IE.2011.60

Filename

6063366