An auditory classifier employing a wavelet neural network implemented in a digital design

Author

Hughes, Jonathan ; Gaborski, Roger ; Hsu, Ken ; Titus, A.

Author_Institution

Rochester Inst. of Technol., Motorola, Austin, TX, USA

fYear

2001

fDate

6/23/1905 12:00:00 AM

Firstpage

8

Lastpage

12

Abstract

This work explores the use of a wavelet transform, a feature extractor mechanism, and a neural network to classify audio samples as belonging to either a voice class, or a music class. The proposed system was implemented in a digital design using VHDL and was synthesized with the Synopsys Design Compiler, using the LSI-10 K synthesized library cells with a clock frequency of 11.025 kHz. This design of a wavelet neural network was effective in correctly identifying the test data sets

Keywords

audio signal processing; circuit CAD; digital integrated circuits; discrete wavelet transforms; feature extraction; integrated circuit design; music; neural chips; pattern classification; signal classification; speech recognition; 11.025 kHz; DWT; LSI-10K synthesized library cells; Synopsys design compiler; VHDL; audio samples classification; auditory classifier; digital design; feature extractor mechanism; music class; voice class; wavelet neural network; wavelet transform; Discrete wavelet transforms; Feature extraction; Fourier transforms; Frequency; Intelligent networks; Low pass filters; Neural networks; Signal analysis; Wavelet analysis; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

ASIC/SOC Conference, 2001. Proceedings. 14th Annual IEEE International

Conference_Location

Arlington, VA

Print_ISBN

0-7803-6741-3

Type

conf

DOI

10.1109/ASIC.2001.954664

Filename

954664