Cover Image

An improved method in speech signal input representation based on DTW technique for NN speech recognition system

A pre-processing of linear predictive coefficient (LPC) features for preparation of reliable reference templates for the set of words to be recognized using the artificial neural network is presented in this paper. The paper also proposes the use of pitch feature derived from the recorded speech dat...

Full description

Saved in:
Bibliographic Details
Main Authors: Sudirman, Rubita, Salleh, Sh. Hussain, Salleh, Shaharuddin
Format: Article
Language:English
English
Published: Penerbit UTM Press 2007
Subjects:
TK Electrical engineering. Electronics Nuclear engineering
Online Access:http://eprints.utm.my/id/eprint/8038/3/281
http://eprints.utm.my/id/eprint/8038/4/RubitaSudirman2007_AnImprovedMethodinSpeechSignal.pdf
http://eprints.utm.my/id/eprint/8038/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.8038
record_format eprints
spelling my.utm.80382017-11-01T04:17:27Z http://eprints.utm.my/id/eprint/8038/ An improved method in speech signal input representation based on DTW technique for NN speech recognition system Sudirman, Rubita Salleh, Sh. Hussain Salleh, Shaharuddin TK Electrical engineering. Electronics Nuclear engineering A pre-processing of linear predictive coefficient (LPC) features for preparation of reliable reference templates for the set of words to be recognized using the artificial neural network is presented in this paper. The paper also proposes the use of pitch feature derived from the recorded speech data as another input feature. The Dynamic Time Warping algorithm (DTW) is the back–bone of the newly developed algorithm called DTW fixing frame algorithm (DTW–FF) which is designed to perform template matching for the input preprocessing. The purpose of the new algorithm is to align the input frames in the test set to the template frames in the reference set. This frame normalization is required since NN is designed to compare data of the same length, however same speech varies in their length most of the time. By doing frame fixing, the input frames and the reference frames are adjusted to the same number of frames according to the reference frames. Another task of the study is to extract pitch features using the Harmonic Filter algorithm. After pitch extraction and linear predictive coefficient (LPC) features fixed to a desired number of frames, speech recognition using neural network can be performed and results showed a very promising solution. Result showed that as high as 98% recognition can be achieved using combination of two features mentioned above. At the end of the paper, a convergence comparison between conjugate gradient descent (CGD), Quasi–Newton, and steepest gradient descent (SGD) search direction is performed and results show that the CGD outperformed the Newton and SGD. Penerbit UTM Press 2007-06 Article PeerReviewed text/html en http://eprints.utm.my/id/eprint/8038/3/281 application/pdf en http://eprints.utm.my/id/eprint/8038/4/RubitaSudirman2007_AnImprovedMethodinSpeechSignal.pdf Sudirman, Rubita and Salleh, Sh. Hussain and Salleh, Shaharuddin (2007) An improved method in speech signal input representation based on DTW technique for NN speech recognition system. Jurnal Teknologi D, 46 (D). pp. 135-149. ISSN 2180-3722 DOI:10.11113/jt.v46.291
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
English
topic TK Electrical engineering. Electronics Nuclear engineering
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Sudirman, Rubita
Salleh, Sh. Hussain
Salleh, Shaharuddin
An improved method in speech signal input representation based on DTW technique for NN speech recognition system
description A pre-processing of linear predictive coefficient (LPC) features for preparation of reliable reference templates for the set of words to be recognized using the artificial neural network is presented in this paper. The paper also proposes the use of pitch feature derived from the recorded speech data as another input feature. The Dynamic Time Warping algorithm (DTW) is the back–bone of the newly developed algorithm called DTW fixing frame algorithm (DTW–FF) which is designed to perform template matching for the input preprocessing. The purpose of the new algorithm is to align the input frames in the test set to the template frames in the reference set. This frame normalization is required since NN is designed to compare data of the same length, however same speech varies in their length most of the time. By doing frame fixing, the input frames and the reference frames are adjusted to the same number of frames according to the reference frames. Another task of the study is to extract pitch features using the Harmonic Filter algorithm. After pitch extraction and linear predictive coefficient (LPC) features fixed to a desired number of frames, speech recognition using neural network can be performed and results showed a very promising solution. Result showed that as high as 98% recognition can be achieved using combination of two features mentioned above. At the end of the paper, a convergence comparison between conjugate gradient descent (CGD), Quasi–Newton, and steepest gradient descent (SGD) search direction is performed and results show that the CGD outperformed the Newton and SGD.
format Article
author Sudirman, Rubita
Salleh, Sh. Hussain
Salleh, Shaharuddin
author_facet Sudirman, Rubita
Salleh, Sh. Hussain
Salleh, Shaharuddin
author_sort Sudirman, Rubita
title An improved method in speech signal input representation based on DTW technique for NN speech recognition system
title_short An improved method in speech signal input representation based on DTW technique for NN speech recognition system
title_full An improved method in speech signal input representation based on DTW technique for NN speech recognition system
title_fullStr An improved method in speech signal input representation based on DTW technique for NN speech recognition system
title_full_unstemmed An improved method in speech signal input representation based on DTW technique for NN speech recognition system
title_sort improved method in speech signal input representation based on dtw technique for nn speech recognition system
publisher Penerbit UTM Press
publishDate 2007
url http://eprints.utm.my/id/eprint/8038/3/281
http://eprints.utm.my/id/eprint/8038/4/RubitaSudirman2007_AnImprovedMethodinSpeechSignal.pdf
http://eprints.utm.my/id/eprint/8038/
_version_ 1643644908148359168
score 13.211869

Similar Items