Speaker-Independent Malay Syllable Recognition Using Singular And Modular Neural Networks

The paper investigates the use of Singular and Modular Neural Networks in classifying the Malay syllable sounds in a speaker-independent manner. The syllable sounds are initialized with plosives and followed by vowels. The speech tokens are sampled at 16 kHz with 16-bit resolution. Linear Predictive...

Full description

Bibliographic Details
Main Authors: Ting, Hua Nong, Yunus, Jasmy, Shaikh Salleh, Sheikh Hussain
Format: Article
Language:English
Published: Penerbit UTM Press 2001
Subjects:
Online Access:http://eprints.utm.my/1491/
http://eprints.utm.my/1491/1/JT35D6.pdf
_version_ 1848890149480431616
author Ting, Hua Nong
Yunus, Jasmy
Shaikh Salleh, Sheikh Hussain
author_facet Ting, Hua Nong
Yunus, Jasmy
Shaikh Salleh, Sheikh Hussain
author_sort Ting, Hua Nong
building UTeM Institutional Repository
collection Online Access
description The paper investigates the use of Singular and Modular Neural Networks in classifying the Malay syllable sounds in a speaker-independent manner. The syllable sounds are initialized with plosives and followed by vowels. The speech tokens are sampled at 16 kHz with 16-bit resolution. Linear Predictive Coding (LPC) is used to extract the speech features. The Neural Networks utilize standard three-layer Multi-Layer Perceptron (MLP) as the speech sound classifier. The MLPs are trained with stochastic Back-Propagation (BP). The weights of the networks are updated after presentation of each training token and the sequence of the epoch is randomized after every epoch. The speech training and test tokens are obtained from 25 (17 females and 8 males) and 4 (all females) Malay adult speakers respectively. The total training and test token number are 1600 and 320 respectively. The result shows that modular neural networks outperform singular neural network with a recognition rate of about 92%.
first_indexed 2025-11-15T20:37:29Z
format Article
id utm-1491
institution Universiti Teknologi Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:37:29Z
publishDate 2001
publisher Penerbit UTM Press
recordtype eprints
repository_type Digital Repository
spelling utm-14912017-11-01T04:17:48Z http://eprints.utm.my/1491/ Speaker-Independent Malay Syllable Recognition Using Singular And Modular Neural Networks Ting, Hua Nong Yunus, Jasmy Shaikh Salleh, Sheikh Hussain TK Electrical engineering. Electronics Nuclear engineering The paper investigates the use of Singular and Modular Neural Networks in classifying the Malay syllable sounds in a speaker-independent manner. The syllable sounds are initialized with plosives and followed by vowels. The speech tokens are sampled at 16 kHz with 16-bit resolution. Linear Predictive Coding (LPC) is used to extract the speech features. The Neural Networks utilize standard three-layer Multi-Layer Perceptron (MLP) as the speech sound classifier. The MLPs are trained with stochastic Back-Propagation (BP). The weights of the networks are updated after presentation of each training token and the sequence of the epoch is randomized after every epoch. The speech training and test tokens are obtained from 25 (17 females and 8 males) and 4 (all females) Malay adult speakers respectively. The total training and test token number are 1600 and 320 respectively. The result shows that modular neural networks outperform singular neural network with a recognition rate of about 92%. Penerbit UTM Press 2001-12 Article PeerReviewed application/pdf en http://eprints.utm.my/1491/1/JT35D6.pdf Ting, Hua Nong and Yunus, Jasmy and Shaikh Salleh, Sheikh Hussain (2001) Speaker-Independent Malay Syllable Recognition Using Singular And Modular Neural Networks. Jurnal Teknologi D (35D). pp. 65-76. ISSN 0127-9696 http://www.penerbit.utm.my/onlinejournal/35/D/JT35D6.pdf
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Ting, Hua Nong
Yunus, Jasmy
Shaikh Salleh, Sheikh Hussain
Speaker-Independent Malay Syllable Recognition Using Singular And Modular Neural Networks
title Speaker-Independent Malay Syllable Recognition Using Singular And Modular Neural Networks
title_full Speaker-Independent Malay Syllable Recognition Using Singular And Modular Neural Networks
title_fullStr Speaker-Independent Malay Syllable Recognition Using Singular And Modular Neural Networks
title_full_unstemmed Speaker-Independent Malay Syllable Recognition Using Singular And Modular Neural Networks
title_short Speaker-Independent Malay Syllable Recognition Using Singular And Modular Neural Networks
title_sort speaker-independent malay syllable recognition using singular and modular neural networks
topic TK Electrical engineering. Electronics Nuclear engineering
url http://eprints.utm.my/1491/
http://eprints.utm.my/1491/
http://eprints.utm.my/1491/1/JT35D6.pdf