Speech recognition based on Kohonen self-organizing feature maps and hybrid connectionist systems - Robotics Institute Carnegie Mellon University

Speech recognition based on Kohonen self-organizing feature maps and hybrid connectionist systems

N. Kasabov, D. Nikovski, and E. Peev
Conference Paper, Proceedings of 1st New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, pp. 113 - 117, November, 1993

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.

BibTeX

@conference{Kasabov-1993-15950,
author = {N. Kasabov and D. Nikovski and E. Peev},
title = {Speech recognition based on Kohonen self-organizing feature maps and hybrid connectionist systems},
booktitle = {Proceedings of 1st New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems},
year = {1993},
month = {November},
pages = {113 - 117},
}