Vowel and consonant recognition in Turkish using neural networks toward continuous speech recognition

Author

Parlaktuna, Osman ; Cakici, Tarkan ; Tora, Hakan ; Barkana, Atalay

Author_Institution

Osmangazi Univ., Eskisehir, Turkey

fYear

1994

fDate

12-14 Apr 1994

Firstpage

55

Abstract

This paper describes an artificial neural network that recognizes vowels and consonants in Turkish when a word or word sequence is uttered. The recognition is performed by three groups of connected nets. Inputs of the nets are the magnitudes of the short time spectrum at 16 mel-scaled frequency points in the range of 240 to 4500 Hz. The first net differentiates the input as being a vowel or a consonant. The outputs of this net as well as the magnitudes of the short time spectrum are used as inputs to the nets for vowel and consonant recognition. Consonant-vowel (CV) or vowel-consonant (VC) fragments of 11 speakers were used for training the different nets, and fragments from 7 more speakers were used for testing

Keywords

neural nets; speech recognition; 16 mel-scaled frequency points; 240 to 4500 Hz; Turkish; connected nets; consonant recognition; continuous speech recognition; neural networks; short time spectrum; testing; training; vowel recognition; word; word sequence; Artificial neural networks; Electronic mail; Frequency; Intelligent networks; Neural networks; Speech recognition; Testing; Training data; Virtual colonoscopy;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrotechnical Conference, 1994. Proceedings., 7th Mediterranean

Conference_Location

Antalya

Print_ISBN

0-7803-1772-6

Type

conf

DOI

10.1109/MELCON.1994.381146

Filename

381146