Malay isolated speech recognition using neural network : a work in finding number of hidden nodes and learning parameters
Joint Authors
Salam, M. D.
Muhammad, Dzulkifli
Salih, Shaykhah
Source
The International Arab Journal of Information Technology
Issue
Vol. 8, Issue 4 (31 Oct. 2011), pp.364-371, 8 p.
Publisher
Publication Date
2011-10-31
Country of Publication
Jordan
No. of Pages
8
Main Subjects
Information Technology and Computer Science
Topics
Abstract EN
This paper explains works in speech recognition using neural network.
The main objective of the experiment is to choose suitable number of nodes in hidden layer and learning parameters for Malay isolated digit speech problem through trial and error method.
The network used in the experiment is feed forward multilayer perceptron trained with back propagation scheme.
Speech data for the study are analyzed using linear predictive coding and log area ratio to represent speech signal for every 20ms through a fixed overlapped windows.
The neural network learning operation is greatly influenced by the parameters i.e., momentum, learning rate and number of hidden nodes chosen.
The result shows that choosing unsuitable parameters lead to unlearned network while some good parameters set from previous work perform badly in this application.
Best recognition rate achieved was 95% using network topology of input nodes, hidden nodes and output nodes of size 320:45:4 respectively while the best momentum rate and learning rate in the experiment were 0.5 and 0.75.
American Psychological Association (APA)
Salam, M. D.& Muhammad, Dzulkifli& Salih, Shaykhah. 2011. Malay isolated speech recognition using neural network : a work in finding number of hidden nodes and learning parameters. The International Arab Journal of Information Technology،Vol. 8, no. 4, pp.364-371.
https://search.emarefa.net/detail/BIM-266753
Modern Language Association (MLA)
Salam, M. D.…[et al.]. Malay isolated speech recognition using neural network : a work in finding number of hidden nodes and learning parameters. The International Arab Journal of Information Technology Vol. 8, no. 4 (Oct. 2011), pp.364-371.
https://search.emarefa.net/detail/BIM-266753
American Medical Association (AMA)
Salam, M. D.& Muhammad, Dzulkifli& Salih, Shaykhah. Malay isolated speech recognition using neural network : a work in finding number of hidden nodes and learning parameters. The International Arab Journal of Information Technology. 2011. Vol. 8, no. 4, pp.364-371.
https://search.emarefa.net/detail/BIM-266753
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 370-371
Record ID
BIM-266753