A connectionist expert approach for speech recognition
Joint Authors
al-Salami, Mukhtar
Bahi, Halimah
Source
The International Arab Journal of Information Technology
Issue
Vol. 2, Issue 2 (30 Apr. 2005), pp.148-153, 6 p.
Publisher
Publication Date
2005-04-30
Country of Publication
Jordan
No. of Pages
6
Main Subjects
Information Technology and Computer Science
Topics
Abstract EN
Artificial Neural Networks (ANNs) are widely and successfully used in speech recognition, but still many limitations are inherited to their topologies and learning style.
In an attempt to overcome these limitations, we combine in a speech recognition hybrid system the pattern processing of ANNs and the logical inferencing of symbolic approaches.
In particular, we are interested in the Connectionist Expert System (CES) introduced by Gallant [10], it consists of an expert system implemented throughout a Multi Layer Perception (MLP).
In such network, each neuron has a symbolic significance.
This will overcome one of the difficulties encountered when we built an MLP, which is how to find the appropriate network configuration and will provide it with explanation capabilities.
In this paper, we present a CES dedicated to Arabic speech recognition.
So, we implemented a neural network where the input neurons represent the acoustical level, they are defined using the vector quantization techniques.
The hidden layer represents the phonetic level and according to the Arabic particularities, the used phonetic unit is the syllable.
Finally, the output neurons stand for the lexical level, since they are the vocabulary words.
American Psychological Association (APA)
Bahi, Halimah& al-Salami, Mukhtar. 2005. A connectionist expert approach for speech recognition. The International Arab Journal of Information Technology،Vol. 2, no. 2, pp.148-153.
https://search.emarefa.net/detail/BIM-12147
Modern Language Association (MLA)
Bahi, Halimah& al-Salami, Mukhtar. A connectionist expert approach for speech recognition. The International Arab Journal of Information Technology Vol. 2, no. 2 (Apr. 2005), pp.148-153.
https://search.emarefa.net/detail/BIM-12147
American Medical Association (AMA)
Bahi, Halimah& al-Salami, Mukhtar. A connectionist expert approach for speech recognition. The International Arab Journal of Information Technology. 2005. Vol. 2, no. 2, pp.148-153.
https://search.emarefa.net/detail/BIM-12147
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 153
Record ID
BIM-12147