Digital signal processor-based feature extraction vocoder for the deaf

Author

Miskiel, Edward ; Özdamar, Özcan ; Oller, D.Kimbrough ; Eilers, Rebecca

Author_Institution

Intelligent Hearing Syst., Miami, FL, USA

fYear

1992

fDate

14-17 Jun 1992

Firstpage

504

Lastpage

509

Abstract

An innovative feature detection tactile vocoder based on linear predictive coding (LPC) processing algorithms is described. The device utilizes the 80386 microprocessor and the TMS320C30 floating point digital signal processor. Speech processing is implemented in real-time. The vocoder algorithms allow the detection of spectral peaks corresponding to the first three formants of the vocal tract as well as fundamental frequency. This LPC approach enhances the ability of vocoders to track formant transitions and fundamental frequency, and it minimizes spatiotemporal masking

Keywords

digital signal processing chips; handicapped aids; speech recognition equipment; vocoders; 80386 microprocessor; TMS320C30 floating point digital signal processor; deaf people; feature detection tactile vocoder; formant transitions; fundamental frequency; linear predictive coding; processing algorithms; spatiotemporal masking; spectral peaks; Computer vision; Digital signal processors; Feature extraction; Frequency; Linear predictive coding; Microprocessors; Signal processing; Signal processing algorithms; Speech processing; Vocoders;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems, 1992. Proceedings., Fifth Annual IEEE Symposium on

Conference_Location

Durham, NC

Print_ISBN

0-8186-2742-5

Type

conf

DOI

10.1109/CBMS.1992.245008

Filename

245008