Speech recognition in the real world: artificial neural networks and robustness

Harouna Kabre

doi:10.1117/12.271715

3 April 1997 Speech recognition in the real world: artificial neural networks and robustness

Harouna Kabre

Proceedings Volume 3078, Wavelet Applications IV; (1997) https://doi.org/10.1117/12.271715
Event: AeroSense '97, 1997, Orlando, FL, United States

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.

Citation Download Citation

Harouna Kabre "Speech recognition in the real world: artificial neural networks and robustness", Proc. SPIE 3078, Wavelet Applications IV, (3 April 1997); https://doi.org/10.1117/12.271715

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available