Title :
A neural net acoustic phonetic feature extractor based on wavelets
Author :
Davenport, Michael R. ; Garudadri, Harinath
Author_Institution :
Dept. of Phys., British Columbia Univ., Vancouver, BC, Canada
Abstract :
An experimental speech processing system for extracting acoustic phonetic features from speaker independent continuous speech has been built and tested. The system uses wavelet analysis to preprocess the speech, and a two-layer receptive field neural network to recognize the phonetic features. The recognizer was implemented in software on a desktop computer, and DARPA´s TIMIT CD-ROM database of continuous speech was used for both training and testing. Preliminary results, using a network trained to recognize voicing and frication, are presented
Keywords :
neural nets; speech analysis and processing; speech recognition; DARPA; TIMIT CD-ROM database; acoustic phonetic feature extractor; desktop computer; frication; neural network; phonetic features recognition; software; speaker independent continuous speech; speech processing system; testing; training; two-layer receptive field; voicing; wavelets; Acoustic testing; Acoustic waves; Feature extraction; Loudspeakers; Neural networks; Speech analysis; Speech processing; Speech recognition; System testing; Wavelet analysis;
Conference_Titel :
Communications, Computers and Signal Processing, 1991., IEEE Pacific Rim Conference on
Conference_Location :
Victoria, BC
Print_ISBN :
0-87942-638-1
DOI :
10.1109/PACRIM.1991.160774
