Spatio-temporal biologically inspired models for clean and noisy speech recognition

Authors:
Zouhour Neji Ben Salem;Laurent Boougrain;Frédéric Alexandre
Affiliations:
AI Unit, CRISTAL Laboratory, National School of Computer Sciences, Manouba Campus, Tunisia;Cortex Team, LORIA Laboratory, Nancy, France;Cortex Team, LORIA Laboratory, Nancy, France
Venue:
Neurocomputing
Year:
2007

Citing 2
Cited 0

Self-Organizing Maps

Self-Organizing Maps
The time-organized map algorithm: extending the self-organizing map to spatiotemporal signals

Neural Computation

Quantified Score

Hi-index	0.03

Visualization

Abstract

Speech perception and recognition using biologically inspired models is a challenging issue not well explored yet. The paper presents two spatio-temporal biologically inspired methods for the preprocessing and learning of speech signal based on self-organization map (SOM). The experimental results are very encouraging and provide a framework that could be more studied to enhance speech perception and recognition technology.