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:
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