A phonetically based small vocabulary automatic speech recognition system

Author

Walker, Katarina ; deSilva, C.J.S. ; Alder, Michael ; Attikiouzel, Yianni ; Hallgren, Richard

Author_Institution

Dept. of Electr. & Electron. Eng., Western Australia Univ., Nedlands, WA, Australia

fYear

1989

fDate

22-24 Nov 1989

Firstpage

765

Lastpage

768

Abstract

A description is presented of a speaker independent automatic speech recognition system for a small vocabulary, employing phonetically based methods. The system uses formant tracking and relative energy values to characterize each word in the vocabulary (the digits, 0 to 9) and also a ratio of energies in the top and bottom half of the frequency band to detect fricatives. The formants are tracked by the second derivative of a smoothed FFT (fast Fourier transform). The system was tested on a number of speakers of both sexes, with encouraging results. Conclusions are drawn about the general feasibility of a formant based approach to automatic speech recognition

Keywords

speech recognition; automatic speech recognition system; fast Fourier transform; formant tracking; formants tracking; frequency band; fricatives; phonetically based methods; relative energy values; second derivative; small vocabulary; smoothed FFT; speaker independent speech recognition; Australia; Automatic speech recognition; Automatic testing; Data acquisition; Frequency; Hidden Markov models; Power engineering and energy; Spectrogram; System testing; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

TENCON '89. Fourth IEEE Region 10 International Conference

Conference_Location

Bombay

Type

conf

DOI

10.1109/TENCON.1989.177050

Filename

177050