Speaker-independent Malay isolated sounds recognition

Author

Ting, Hua Nong ; Yunus, Jmmy ; Wong, Lee Chen

Author_Institution

Dept. of Electron., Universiti Teknologi Malaysia, Johor, Malaysia

Volume

5

fYear

2002

fDate

18-22 Nov. 2002

Firstpage

2405

Abstract

This paper simply describes the use of neural networks in recognizing some Malay isolated sounds of Malay children in a speaker-independent manner. The isolated sounds are Malay plosive sounds, which are comprised of /b/, /d/, /g/, /p/, /t/ and /k/. A three-layer Multi-layer Perceptron (MLP) is used to train and recognize the speech sounds. The MLP output layer has an output layer of 6 neurons, which correspond to the 6 isolated plosive sounds. Network parameters such as hidden neuron number and error function, were investigated to achieve the optimal performance of the MLP. The proposed system was able to achieve the highest accuracy of 84.67%.

Keywords

backpropagation; feature extraction; linear predictive coding; multilayer perceptrons; speech recognition; Malay isolated sounds recognition; Malay plosive sounds; error function; hidden neuron number; linear predictive coding; neural networks; optimal performance; speaker-independent recognition; speech database; speech feature extraction; stochastic backpropagation; three-layer multilayer perceptron; Cepstral analysis; Feature extraction; Linear predictive coding; Loudspeakers; Multilayer perceptrons; Neural networks; Neurons; Spatial databases; Speech coding; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on

Print_ISBN

981-04-7524-1

Type

conf

DOI

10.1109/ICONIP.2002.1201925

Filename

1201925