An analog integrated speech front-end based on the auditory periphery

Author

Liu, Weimin ; Andreou, Andreas G. ; Goldstein, Moise H., Jr.

Author_Institution

Dept. of Electr. & Comput. Eng., Johns Hopkins Univ., Baltimore, MD, USA

fYear

1991

fDate

8-14 Jul 1991

Firstpage

861

Abstract

The authors present an analog CMOS integrated circuit realization of an auditory periphery model which includes the middle ear, the basilar membrane, and the hair cells/synapses. With speech input, the pattern of the multichannel outputs resembles the neurogram of the auditory nerve fibers, i.e. the time-varying instantaneous firing rates of fibers having different characteristic frequencies. This real-time low-power-dissipation speech preprocessor can be used as the front-end to practical speech processing and recognition systems

Keywords

CMOS integrated circuits; neural nets; speech analysis and processing; speech recognition; CMOS integrated circuit realization; analog integrated speech front-end; auditory periphery; basilar membrane; hair cells; middle ear; multichannel outputs; neurogram; speech preprocessor; speech recognition; synapses; time-varying instantaneous firing rates; Biomembranes; CMOS analog integrated circuits; Ear; Frequency; Hair; Integrated circuit modeling; Nerve fibers; Real time systems; Semiconductor device modeling; Speech processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on

Conference_Location

Seattle, WA

Print_ISBN

0-7803-0164-1

Type

conf

DOI

10.1109/IJCNN.1991.155447

Filename

155447