Speaker Identification Using Wavelet Packet Transform and Feed Forward Neural Network

It has been known for a long time that speakers can be identified from their voices. In this work we introduce a speaker identification system using wavelet packet transform. This is one of a wavelet transform analysis for feature extraction and a neural network for classification. This system is ap...

Full description

Saved in:

Bibliographic Details
Main Author:	Almashrgy, Mohamed Ali
Format:	Thesis
Language:	English English
Published:	2005
Subjects:	Neural networks (Computer science)
Online Access:	http://psasir.upm.edu.my/id/eprint/865/2/FK_2005_36A.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-upm-ir.865
record_format	uketd_dc
spelling	my-upm-ir.8652013-05-27T06:51:11Z Speaker Identification Using Wavelet Packet Transform and Feed Forward Neural Network 2005-03 Almashrgy, Mohamed Ali It has been known for a long time that speakers can be identified from their voices. In this work we introduce a speaker identification system using wavelet packet transform. This is one of a wavelet transform analysis for feature extraction and a neural network for classification. This system is applied on ten speakers Instead of applying framing on the signal, the wavelet packet transform is applied on the whole range of the signal. This reduces the calculation time. The speech signal is decomposed into 24 sub bands, according to Mel-scale frequency. Then, for each of these bands, the log energy is taken. Finally, the discrete cosine transform is applied on these bands. These are taken as features for identifying the speaker among many speakers. For the classification task, Feed Forward multi layer perceptron, trained by backpropagation, is proposed for use as training and classification feature vectors of the speaker. We propose to construct a single neural network for each speaker of interest. Training and testing of isolated words in three cases, Vis one-, two-, and three-syllable words, were obtained by recording these words from the LAB colleagues using a low-cost microphone. Neural networks (Computer science) 2005-03 Thesis http://psasir.upm.edu.my/id/eprint/865/ http://psasir.upm.edu.my/id/eprint/865/2/FK_2005_36A.pdf application/pdf en public masters Universiti Putra Malaysia Neural networks (Computer science) Faculty of Engineering English
institution	Universiti Putra Malaysia
collection	PSAS Institutional Repository
language	English English
topic	Neural networks (Computer science)
spellingShingle	Neural networks (Computer science) Almashrgy, Mohamed Ali Speaker Identification Using Wavelet Packet Transform and Feed Forward Neural Network
description	It has been known for a long time that speakers can be identified from their voices. In this work we introduce a speaker identification system using wavelet packet transform. This is one of a wavelet transform analysis for feature extraction and a neural network for classification. This system is applied on ten speakers Instead of applying framing on the signal, the wavelet packet transform is applied on the whole range of the signal. This reduces the calculation time. The speech signal is decomposed into 24 sub bands, according to Mel-scale frequency. Then, for each of these bands, the log energy is taken. Finally, the discrete cosine transform is applied on these bands. These are taken as features for identifying the speaker among many speakers. For the classification task, Feed Forward multi layer perceptron, trained by backpropagation, is proposed for use as training and classification feature vectors of the speaker. We propose to construct a single neural network for each speaker of interest. Training and testing of isolated words in three cases, Vis one-, two-, and three-syllable words, were obtained by recording these words from the LAB colleagues using a low-cost microphone.
format	Thesis
qualification_level	Master's degree
author	Almashrgy, Mohamed Ali
author_facet	Almashrgy, Mohamed Ali
author_sort	Almashrgy, Mohamed Ali
title	Speaker Identification Using Wavelet Packet Transform and Feed Forward Neural Network
title_short	Speaker Identification Using Wavelet Packet Transform and Feed Forward Neural Network
title_full	Speaker Identification Using Wavelet Packet Transform and Feed Forward Neural Network
title_fullStr	Speaker Identification Using Wavelet Packet Transform and Feed Forward Neural Network
title_full_unstemmed	Speaker Identification Using Wavelet Packet Transform and Feed Forward Neural Network
title_sort	speaker identification using wavelet packet transform and feed forward neural network
granting_institution	Universiti Putra Malaysia
granting_department	Faculty of Engineering
publishDate	2005
url	http://psasir.upm.edu.my/id/eprint/865/2/FK_2005_36A.pdf
_version_	1747810283452104704

Speaker Identification Using Wavelet Packet Transform and Feed Forward Neural Network

Similar Items