Digit recognition using neural networks

This paper investigates the use of feed-forward multi-layer perceptrons trained by back-propagation in speech recognition. Besides this, the paper also proposes an automatic technique for both training and recognition. The use of neural networks for speaker independent isolated word recognition on s...

Full description

Bibliographic Details
Main Authors: Tan, Chin Luh, Jantan, Adznan
Format: Article
Language:English
Published: Faculty of Computer Science and Information Technology, University of Malaya 2004
Online Access:http://psasir.upm.edu.my/id/eprint/49491/
http://psasir.upm.edu.my/id/eprint/49491/1/Digit%20recognition%20using%20neural%20networks.pdf
_version_ 1848851282819809280
author Tan, Chin Luh
Jantan, Adznan
author_facet Tan, Chin Luh
Jantan, Adznan
author_sort Tan, Chin Luh
building UPM Institutional Repository
collection Online Access
description This paper investigates the use of feed-forward multi-layer perceptrons trained by back-propagation in speech recognition. Besides this, the paper also proposes an automatic technique for both training and recognition. The use of neural networks for speaker independent isolated word recognition on small vocabularies is studied and an automated system from the training stage to the recognition stage without the need of manual cropping for speech signals is developed to evaluate the performance of the automatic speech recognition (ASR) system. Linear predictive coding (LPC) has been applied to represent speech signal in frames in early stage. Features from the selected frames are used to train multilayer perceptrons (MLP) using back-propagation. The same routine is applied to the speech signal during the recognition stage and unknown test patterns are classified to the nearest patterns. In short, the selected frames represent the local features of the speech signal and all of them contribute to the global similarity for the whole speech signal. The analysis, design and development of the automation system are done in MATLAB, in which an isolated word speaker independent digits recogniser is developed.
first_indexed 2025-11-15T10:19:43Z
format Article
id upm-49491
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T10:19:43Z
publishDate 2004
publisher Faculty of Computer Science and Information Technology, University of Malaya
recordtype eprints
repository_type Digital Repository
spelling upm-494912016-12-30T03:07:26Z http://psasir.upm.edu.my/id/eprint/49491/ Digit recognition using neural networks Tan, Chin Luh Jantan, Adznan This paper investigates the use of feed-forward multi-layer perceptrons trained by back-propagation in speech recognition. Besides this, the paper also proposes an automatic technique for both training and recognition. The use of neural networks for speaker independent isolated word recognition on small vocabularies is studied and an automated system from the training stage to the recognition stage without the need of manual cropping for speech signals is developed to evaluate the performance of the automatic speech recognition (ASR) system. Linear predictive coding (LPC) has been applied to represent speech signal in frames in early stage. Features from the selected frames are used to train multilayer perceptrons (MLP) using back-propagation. The same routine is applied to the speech signal during the recognition stage and unknown test patterns are classified to the nearest patterns. In short, the selected frames represent the local features of the speech signal and all of them contribute to the global similarity for the whole speech signal. The analysis, design and development of the automation system are done in MATLAB, in which an isolated word speaker independent digits recogniser is developed. Faculty of Computer Science and Information Technology, University of Malaya 2004 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/49491/1/Digit%20recognition%20using%20neural%20networks.pdf Tan, Chin Luh and Jantan, Adznan (2004) Digit recognition using neural networks. Malaysian Journal of Computer Science, 17 (2). pp. 40-54. ISSN 0127-9084 http://e-journal.um.edu.my/publish/MJCS/146-161
spellingShingle Tan, Chin Luh
Jantan, Adznan
Digit recognition using neural networks
title Digit recognition using neural networks
title_full Digit recognition using neural networks
title_fullStr Digit recognition using neural networks
title_full_unstemmed Digit recognition using neural networks
title_short Digit recognition using neural networks
title_sort digit recognition using neural networks
url http://psasir.upm.edu.my/id/eprint/49491/
http://psasir.upm.edu.my/id/eprint/49491/
http://psasir.upm.edu.my/id/eprint/49491/1/Digit%20recognition%20using%20neural%20networks.pdf