Vowel articulation training aid for the deaf

Author

Zahorian, Stephen ; Venkat, Subhashri

Author_Institution

Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA

fYear

1990

fDate

3-6 Apr 1990

Firstpage

1121

Abstract

The signal processing strategy for a computer-based vowel articulation training aid for the deaf is described. This processing is based on a nonlinear/linear artificial neural network transformation of 16-channel filter bank data to a two-dimensional space which approximates an F1/F2 space. Speaker-independent vowel training displays have been developed with vowel identity cued by spatial location and color. Testing with both normally-hearing and hearing-impared listeners indicates that the display is very easy to interpret and that the relationship between the pattern and the spoken vowel is consistent. The continuous relationship between phonetic perception and display patterns provides feedback for fine tuning of vocal tract settings

Keywords

acoustic signal processing; computerised signal processing; handicapped aids; neural nets; speech recognition; acoustic-phonetic transformation; computer-based vowel articulation training aid; deaf; hearing-impared listeners; nonlinear/linear artificial neural network; phonetic perception; real-time visual speech display; signal processing; speaker-independent speech recognition; Artificial neural networks; Auditory system; Computer displays; Data mining; Deafness; Feedback; Filter bank; Frequency; Medical treatment; Signal processing; Speech; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.116139

Filename

116139