DocumentCode
3250874
Title
Dynamic time warping using an artificial neural network
Author
Unal, Fatih A. ; Tepedelenlioglu, Nazif
Author_Institution
Siemens Stromberg-Carlson, Boca Raton, FL, USA
Volume
4
fYear
1992
fDate
7-11 Jun 1992
Firstpage
715
Abstract
A dynamic time warping (DTW) algorithm using the Hopfield neural network is described. A DTW energy function is constructed to achieve an optimum match between a reference and a test signal and mapped to the network´s Lyapunov function to determine the connection weights and the biases for the neurons. The experimental results verify that the Hopfield network can be effectively used to solve this optimization problem
Keywords
Hopfield neural nets; Lyapunov methods; dynamic programming; speech recognition; Hopfield neural network; Lyapunov function; artificial neural network; connection weights; dynamic time warping; energy function; neurons; optimization; optimum match; speech recognition; Acoustical engineering; Artificial neural networks; Hopfield neural networks; Neural networks; Neurons; Pattern recognition; Power engineering and energy; Speech recognition; Symmetric matrices; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location
Baltimore, MD
Print_ISBN
0-7803-0559-0
Type
conf
DOI
10.1109/IJCNN.1992.227234
Filename
227234
Link To Document