Speaker Independent Speech Recognition Using Neural Network

In spite of the advances accomplished throughout the last few decades, automatic speech recognition (ASR) is still a challenging and difficult task when the systems are applied in the real world. Different requirements for various applications drive the researchers to explore for more effective w...

全面介紹

Saved in:
書目詳細資料
主要作者: Tan, Chin Luh
格式: Thesis
語言:English
出版: 2004
主題:
在線閱讀:http://psasir.upm.edu.my/id/eprint/37/1/1000548949_t_FK_2004_90.pdf
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
id my-upm-ir.37
record_format uketd_dc
spelling my-upm-ir.372015-08-06T01:49:29Z Speaker Independent Speech Recognition Using Neural Network 2004-12 Tan, Chin Luh In spite of the advances accomplished throughout the last few decades, automatic speech recognition (ASR) is still a challenging and difficult task when the systems are applied in the real world. Different requirements for various applications drive the researchers to explore for more effective ways in the particular application. Attempts to apply artificial neural networks (ANN) as a classification tool are proposed to increase the reliability of the system. This project studies the approach of using neural network for speaker independent isolated word recognition on small vocabularies and proposes a method to have a simple MLP as speech recognizer. Our approach is able to overcome the current limitations of MLP in the selection of input buffers’ size by proposing a method on frames selection. 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 the multilayer perceptrons (MLP) feedforward back-propagation (FFBP) neural network during the training stage. Same routine has been applied to the speech signal during the recognition stage and the unknown test pattern will be classified to one of the nearest pattern. 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 the PC based voice dialling system is developed using MATLAB®. Neural Network 2004-12 Thesis http://psasir.upm.edu.my/id/eprint/37/ http://psasir.upm.edu.my/id/eprint/37/1/1000548949_t_FK_2004_90.pdf application/pdf en public masters Universiti Putra Malaysia Neural Network Faculty of Engineering
institution Universiti Putra Malaysia
collection PSAS Institutional Repository
language English
topic Neural Network


spellingShingle Neural Network


Tan, Chin Luh
Speaker Independent Speech Recognition Using Neural Network
description In spite of the advances accomplished throughout the last few decades, automatic speech recognition (ASR) is still a challenging and difficult task when the systems are applied in the real world. Different requirements for various applications drive the researchers to explore for more effective ways in the particular application. Attempts to apply artificial neural networks (ANN) as a classification tool are proposed to increase the reliability of the system. This project studies the approach of using neural network for speaker independent isolated word recognition on small vocabularies and proposes a method to have a simple MLP as speech recognizer. Our approach is able to overcome the current limitations of MLP in the selection of input buffers’ size by proposing a method on frames selection. 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 the multilayer perceptrons (MLP) feedforward back-propagation (FFBP) neural network during the training stage. Same routine has been applied to the speech signal during the recognition stage and the unknown test pattern will be classified to one of the nearest pattern. 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 the PC based voice dialling system is developed using MATLAB®.
format Thesis
qualification_level Master's degree
author Tan, Chin Luh
author_facet Tan, Chin Luh
author_sort Tan, Chin Luh
title Speaker Independent Speech Recognition Using Neural Network
title_short Speaker Independent Speech Recognition Using Neural Network
title_full Speaker Independent Speech Recognition Using Neural Network
title_fullStr Speaker Independent Speech Recognition Using Neural Network
title_full_unstemmed Speaker Independent Speech Recognition Using Neural Network
title_sort speaker independent speech recognition using neural network
granting_institution Universiti Putra Malaysia
granting_department Faculty of Engineering
publishDate 2004
url http://psasir.upm.edu.my/id/eprint/37/1/1000548949_t_FK_2004_90.pdf
_version_ 1747810153026027520