DocumentCode
313634
Title
Multiresolution elementary tonotopic features for speech perception
Author
Tsiang, Elaine Y L
Author_Institution
Monowave Corp., Seattle, WA, USA
Volume
1
fYear
1997
fDate
9-12 Jun 1997
Firstpage
575
Abstract
We define multiresolution elementary tonotopic features (ETFs) in general, and present specific functions and decompositions for computing them. Such decompositions, when cast in the form of local, fixed-weight FIR neural networks, have definite architectures. Results of their use as front-end inputs to a speaker-independent continuous-speech phoneme recognizer are encouraging. We analyze the dependence of the recognition performance on the various ETFs at different levels of resolution
Keywords
FIR filters; natural language interfaces; neural nets; speech recognition; transforms; front-end inputs; local fixed-weight FIR neural networks; multiresolution elementary tonotopic features; speaker-independent continuous-speech phoneme recognizer; speech perception; Bandwidth; Computer architecture; Computer vision; Feature extraction; Finite impulse response filter; Frequency modulation; Neural networks; Performance analysis; Sampling methods; Speech;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks,1997., International Conference on
Conference_Location
Houston, TX
Print_ISBN
0-7803-4122-8
Type
conf
DOI
10.1109/ICNN.1997.611733
Filename
611733
Link To Document