Endpoint detection enhancement for speaker dependent recognition

The automatic speech recognition (ASR) field has become one of the leading speech technology areas today. Various methods have been introduced to develop an efficient ASR system. The Neural Network (NN) approach is one of the more popular methods that is widely used in this field. Another Multilayer...

Full description

Bibliographic Details
Main Authors:	Ummu Salmah Mohamad, Siti Mariyam Shamsuddsuddsuddsuddin, Ramlan Mahmud
Format:	Article
Published:	Penerbit UKM 2009
Online Access:	http://journalarticle.ukm.my/3501/ http://journalarticle.ukm.my/3501/

id	ukm-3501
recordtype	eprints
spelling	ukm-35012012-02-14T07:23:49Z http://journalarticle.ukm.my/3501/ Endpoint detection enhancement for speaker dependent recognition Ummu Salmah Mohamad, Siti Mariyam Shamsuddsuddsuddsuddin, Ramlan Mahmud, The automatic speech recognition (ASR) field has become one of the leading speech technology areas today. Various methods have been introduced to develop an efficient ASR system. The Neural Network (NN) approach is one of the more popular methods that is widely used in this field. Another Multilayer perceptron (MLP) model which is popularly used in the ASR field is the NN model. However, the current problems faced by MLP and most NN models in the ASR field is the long duration of training. Furthermore, the robustness of the isolated digit recognition is not trivial because it has been widely used in many applications. This study focuses on improving the training time and robustness of the MLP neural network for the Malay isolated digit recognition system by proposing variance endpoint detection to accelerate the convergence time of the NN and to produce the highest recognition accuracy. The proposed endpoint method have shown very promising results over experiments carried out. The overall performance for the Malay data set is 99.83% with a convergence time of 82 seconds. Penerbit UKM 2009-12 Article PeerReviewed Ummu Salmah Mohamad, and Siti Mariyam Shamsuddsuddsuddsuddin, and Ramlan Mahmud, (2009) Endpoint detection enhancement for speaker dependent recognition. Jurnal Teknologi Maklumat dan Multimedia, 7 . pp. 17-29. ISSN 1823-0113 http://www.ukm.my/jitm/vol7_Dec_2009_17-29.html
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Kebangasaan Malaysia
building	UKM Institutional Repository
collection	Online Access
description	The automatic speech recognition (ASR) field has become one of the leading speech technology areas today. Various methods have been introduced to develop an efficient ASR system. The Neural Network (NN) approach is one of the more popular methods that is widely used in this field. Another Multilayer perceptron (MLP) model which is popularly used in the ASR field is the NN model. However, the current problems faced by MLP and most NN models in the ASR field is the long duration of training. Furthermore, the robustness of the isolated digit recognition is not trivial because it has been widely used in many applications. This study focuses on improving the training time and robustness of the MLP neural network for the Malay isolated digit recognition system by proposing variance endpoint detection to accelerate the convergence time of the NN and to produce the highest recognition accuracy. The proposed endpoint method have shown very promising results over experiments carried out. The overall performance for the Malay data set is 99.83% with a convergence time of 82 seconds.
format	Article
author	Ummu Salmah Mohamad, Siti Mariyam Shamsuddsuddsuddsuddin, Ramlan Mahmud,
spellingShingle	Ummu Salmah Mohamad, Siti Mariyam Shamsuddsuddsuddsuddin, Ramlan Mahmud, Endpoint detection enhancement for speaker dependent recognition
author_facet	Ummu Salmah Mohamad, Siti Mariyam Shamsuddsuddsuddsuddin, Ramlan Mahmud,
author_sort	Ummu Salmah Mohamad,
title	Endpoint detection enhancement for speaker dependent recognition
title_short	Endpoint detection enhancement for speaker dependent recognition
title_full	Endpoint detection enhancement for speaker dependent recognition
title_fullStr	Endpoint detection enhancement for speaker dependent recognition
title_full_unstemmed	Endpoint detection enhancement for speaker dependent recognition
title_sort	endpoint detection enhancement for speaker dependent recognition
publisher	Penerbit UKM
publishDate	2009
url	http://journalarticle.ukm.my/3501/ http://journalarticle.ukm.my/3501/
first_indexed	2023-09-18T19:38:58Z
last_indexed	2023-09-18T19:38:58Z
_version_	1777405461508653056

Endpoint detection enhancement for speaker dependent recognition

Similar Items