Hybrid Method for Digits Recognition using Fixed-Frame Scores and Derived Pitch

This paper presents a procedure of frame normalization based on the traditional dynamic time warping (DTW) using the LPC coefficients. The redefined method is called as the DTW frame-fixing method (DTW-FF), it works by normalizing the word frames of the input against the reference frames. The enthu...

Full description

Bibliographic Details
Main Authors: Sudirman, Rubita, Salleh, Sh-Hussain, Salleh, Shaharuddin
Format: Article
Language:English
Published: Springer 2006
Subjects:
Online Access:http://eprints.utm.my/1671/
http://eprints.utm.my/1671/1/rubita06_Hybrid_methods_for_SR.pdf
_version_ 1848890184477704192
author Sudirman, Rubita
Salleh, Sh-Hussain
Salleh, Shaharuddin
author_facet Sudirman, Rubita
Salleh, Sh-Hussain
Salleh, Shaharuddin
author_sort Sudirman, Rubita
building UTeM Institutional Repository
collection Online Access
description This paper presents a procedure of frame normalization based on the traditional dynamic time warping (DTW) using the LPC coefficients. The redefined method is called as the DTW frame-fixing method (DTW-FF), it works by normalizing the word frames of the input against the reference frames. The enthusiasm to this study is due to neural network limitation that entails a fix number of input nodes for when processing multiple inputs in parallel. Due to this problem, this research is initiated to reduce the amount of computation and complexity in a neural network by reducing the number of inputs into the network. In this study, dynamic warping process is used, in which local distance scores of the warping path are fixed and collected so that their scores are of equal number of frames. Also studied in this paper is the consideration of pitch as a contributing feature to the speech recognition. Results showed a good performance and improvement when using pitch along with DTW-FF feature. The convergence rate between using the steepest gradient descent is also compared to another method namely conjugate gradient method. Convergence rate is also improved when conjugate gradient method is introduced in the back-propagation algorithm.
first_indexed 2025-11-15T20:38:02Z
format Article
id utm-1671
institution Universiti Teknologi Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:38:02Z
publishDate 2006
publisher Springer
recordtype eprints
repository_type Digital Repository
spelling utm-16712010-06-01T02:57:07Z http://eprints.utm.my/1671/ Hybrid Method for Digits Recognition using Fixed-Frame Scores and Derived Pitch Sudirman, Rubita Salleh, Sh-Hussain Salleh, Shaharuddin TK Electrical engineering. Electronics Nuclear engineering This paper presents a procedure of frame normalization based on the traditional dynamic time warping (DTW) using the LPC coefficients. The redefined method is called as the DTW frame-fixing method (DTW-FF), it works by normalizing the word frames of the input against the reference frames. The enthusiasm to this study is due to neural network limitation that entails a fix number of input nodes for when processing multiple inputs in parallel. Due to this problem, this research is initiated to reduce the amount of computation and complexity in a neural network by reducing the number of inputs into the network. In this study, dynamic warping process is used, in which local distance scores of the warping path are fixed and collected so that their scores are of equal number of frames. Also studied in this paper is the consideration of pitch as a contributing feature to the speech recognition. Results showed a good performance and improvement when using pitch along with DTW-FF feature. The convergence rate between using the steepest gradient descent is also compared to another method namely conjugate gradient method. Convergence rate is also improved when conjugate gradient method is introduced in the back-propagation algorithm. Springer 2006-12-11 Article NonPeerReviewed application/pdf en http://eprints.utm.my/1671/1/rubita06_Hybrid_methods_for_SR.pdf Sudirman, Rubita and Salleh, Sh-Hussain and Salleh, Shaharuddin (2006) Hybrid Method for Digits Recognition using Fixed-Frame Scores and Derived Pitch. Proceeding of 3rd Kuala Lumpur International Conference on Biomedical Engineering, 15 . pp. 67-71. ISSN 1727-1983
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Sudirman, Rubita
Salleh, Sh-Hussain
Salleh, Shaharuddin
Hybrid Method for Digits Recognition using Fixed-Frame Scores and Derived Pitch
title Hybrid Method for Digits Recognition using Fixed-Frame Scores and Derived Pitch
title_full Hybrid Method for Digits Recognition using Fixed-Frame Scores and Derived Pitch
title_fullStr Hybrid Method for Digits Recognition using Fixed-Frame Scores and Derived Pitch
title_full_unstemmed Hybrid Method for Digits Recognition using Fixed-Frame Scores and Derived Pitch
title_short Hybrid Method for Digits Recognition using Fixed-Frame Scores and Derived Pitch
title_sort hybrid method for digits recognition using fixed-frame scores and derived pitch
topic TK Electrical engineering. Electronics Nuclear engineering
url http://eprints.utm.my/1671/
http://eprints.utm.my/1671/1/rubita06_Hybrid_methods_for_SR.pdf