Share Email Print
cover

Proceedings Paper

Speech recognition in the real world: artificial neural networks and robustness
Author(s): Harouna Kabre
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents an empirical modeling of the role of environment for Automatic Speech Recognition systems in real world, taken in the framework of an Artificial Life methodology. Environment is modeled as an active system which triggers the shift between the training and testing states of automatic speech recognition systems (ASRSs) which are built from ANNs. First an initial set of ASRSs are created to recognize speech under the constraints of an unpredictable acoustic world. The training of the ASRSs starts and goes on until ASRSs no longer decrease their error classification in the current acoustic environment because of noises. This moment is detected by the reactive environment and the structure of the ASRSs are changed. The simulation performed with mathematical models of real rooms as environment showed that our system could be used as a prediction tool of ASRSs performances for the study of any speech perceiver based on ANNs or on hidden Markov models. Moreover, it is shown that on a task of French digits recognition, the new method performs better than conventional ones.

Paper Details

Date Published: 3 April 1997
PDF: 7 pages
Proc. SPIE 3078, Wavelet Applications IV, (3 April 1997); doi: 10.1117/12.271715
Show Author Affiliations
Harouna Kabre, Joseph Fourier Univ. (France)


Published in SPIE Proceedings Vol. 3078:
Wavelet Applications IV
Harold H. Szu, Editor(s)

© SPIE. Terms of Use
Back to Top