Title :
Learning vector quantization, multi layer perceptron and dynamic programming: comparison and cooperation
Author :
Driancourt, Xavier ; Bottou, Léon ; Gallinari, Patrick
Author_Institution :
LRI Univ. Paris Sud, Orsay, France
Abstract :
The authors compare dynamic programming, or DP, multilayer perceptron, time-delay neural network, or TDNN, shift-tolerant learning vector quantization, and K-means on a multispeaker isolated-word small vocabulary problem. A suboptimal cooperation between TDNN and other algorithms is proposed and successfully tested on the problem. The combination of TDNN and DP performs especially well. An optimal cooperation method between DP and some other algorithms is proposed
Keywords :
delays; dynamic programming; learning systems; neural nets; speech recognition; K-means; learning; multilayer perceptron; multispeaker isolated-word small vocabulary problem; suboptimal cooperation; time-delay neural network; vector quantisation; Databases; Dynamic programming; Event detection; Hidden Markov models; Neural networks; Speech recognition; Stochastic processes; Testing; Vector quantization; Vocabulary;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155439
