A study of speech recognition system based on the Hidden Markov Model with Gaussian-Mixture

Author

Ben Hazem, Zied ; Zouhir, Youssef ; Ouni, Kais

Author_Institution

Higher Sch. of Technol. & Comput. Sci. (ESTI), Univ. of Carthage, Tunis, Tunisia

fYear

2014

Firstpage

1

Lastpage

5

Abstract

In this paper, we present a study of isolated word speech recognition system. The adopted system is based on the Hidden Markov Model with Gaussian Mixture (HMM-GM). We studied the recognition rate by varying the states number (3, 4, 5, 6 and 7 states) and the number of Gaussians per state (2, 4, 8, 12, 14 and 16 Gaussians) of Hidden Markov Model. We evaluated these recognition rates using two parameterization techniques Mel Frequency Cepstral Coefficients (MFCC) and Perceptual Linear Prediction (PLP). We have introduced the dynamic coefficients and the energy of the signal in order to achieve an improvement in the recognition rate.

Keywords

Gaussian processes; hidden Markov models; mixture models; prediction theory; speech recognition; Gaussian-mixture model; HMM-GM model; MFCC; PLP; hidden Markov model; isolated word speech recognition system; mel frequency cepstral coefficient; parameterization technique; perceptual linear prediction; Automatic speech recognition; Hidden Markov models; Markov processes; Mel frequency cepstral coefficient; Reconnaissance; Speech;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Sciences and Technologies in Maghreb (CISTEM), 2014 International Conference on

Type

conf

DOI

10.1109/CISTEM.2014.7076916

Filename

7076916