DocumentCode :
2066816
Title :
Speech recognition based on Kohonen self-organizing feature maps and hybrid connectionist systems
Author :
Kasabov, N. ; Nikovski, D. ; Peev, E.
Author_Institution :
Dept. of Inf. Sci., Otago Univ., Dunedin, New Zealand
fYear :
1993
fDate :
24-26 Nov 1993
Firstpage :
113
Lastpage :
117
Abstract :
Describes a series of experiments on using Kohonen self-organizing maps and hybrid systems for continuous speech recognition. Experiments with different nonlinear transformations on the signal before using a neural network has been done and results compared. The hybrid system developed by the authors combines self-organizing feature maps with dynamic time warping. The experiments suggest that the combination has better performance than either of the two methods applied individually
Keywords :
self-organising feature maps; speech recognition; Kohonen self-organizing feature maps; continuous speech recognition; dynamic time warping; hybrid connectionist systems; neural network; nonlinear signal transformations; performance; Frequency; Hidden Markov models; Information science; Neural networks; Nonlinear distortion; Nonlinear dynamical systems; Self organizing feature maps; Speech recognition; Vectors; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Artificial Neural Networks and Expert Systems, 1993. Proceedings., First New Zealand International Two-Stream Conference on
Conference_Location :
Dunedin
Print_ISBN :
0-8186-4260-2
Type :
conf
DOI :
10.1109/ANNES.1993.323068
Filename :
323068
Link To Document :
بازگشت