A WAVELET NEURAL NETWORK RAMWORK FOR SPEAKER IDNTIFCATION
This paper introduces a new model-free identification methodology to detect and identify speakers and recognize them. The basic module of the methodology is a novel multi-dimensional wavelet neural network. The WNN approach include: a universal approximator; the time frequency localization: propert...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
University of Baghdad
2006-03-01
|
Series: | Journal of Engineering |
Online Access: | https://www.joe.uobaghdad.edu.iq/index.php/main/article/view/2963 |
_version_ | 1797267057895538688 |
---|---|
author | W. A. Mahmoud Dhiadeen.M. Salih Saleem M-R. Taha |
author_facet | W. A. Mahmoud Dhiadeen.M. Salih Saleem M-R. Taha |
author_sort | W. A. Mahmoud |
collection | DOAJ |
description |
This paper introduces a new model-free identification methodology to detect and identify speakers and recognize them. The basic module of the methodology is a novel multi-dimensional wavelet neural network. The WNN approach include: a universal approximator; the time frequency localization: property of wavelets leads to reduced networks at a given level of performance; The construct used as the feature mode classifier. Wavelet transform has been successfully applied to the processing of non- stationary speech signal and the feature vector that obtained becomes the input to the wavelet neural network which is trained off-line to map features to used for the classification procedure. An example is employed to illustrate the robustness and effectiveness of the proposed scheme
|
first_indexed | 2024-03-07T15:36:50Z |
format | Article |
id | doaj.art-8adfe1ee06a845d5a09309512f39393a |
institution | Directory Open Access Journal |
issn | 1726-4073 2520-3339 |
language | English |
last_indexed | 2024-04-25T01:10:32Z |
publishDate | 2006-03-01 |
publisher | University of Baghdad |
record_format | Article |
series | Journal of Engineering |
spelling | doaj.art-8adfe1ee06a845d5a09309512f39393a2024-03-10T09:52:23ZengUniversity of BaghdadJournal of Engineering1726-40732520-33392006-03-01120110.31026/j.eng.2006.01.17A WAVELET NEURAL NETWORK RAMWORK FOR SPEAKER IDNTIFCATIONW. A. MahmoudDhiadeen.M. SalihSaleem M-R. Taha This paper introduces a new model-free identification methodology to detect and identify speakers and recognize them. The basic module of the methodology is a novel multi-dimensional wavelet neural network. The WNN approach include: a universal approximator; the time frequency localization: property of wavelets leads to reduced networks at a given level of performance; The construct used as the feature mode classifier. Wavelet transform has been successfully applied to the processing of non- stationary speech signal and the feature vector that obtained becomes the input to the wavelet neural network which is trained off-line to map features to used for the classification procedure. An example is employed to illustrate the robustness and effectiveness of the proposed scheme https://www.joe.uobaghdad.edu.iq/index.php/main/article/view/2963 |
spellingShingle | W. A. Mahmoud Dhiadeen.M. Salih Saleem M-R. Taha A WAVELET NEURAL NETWORK RAMWORK FOR SPEAKER IDNTIFCATION Journal of Engineering |
title | A WAVELET NEURAL NETWORK RAMWORK FOR SPEAKER IDNTIFCATION |
title_full | A WAVELET NEURAL NETWORK RAMWORK FOR SPEAKER IDNTIFCATION |
title_fullStr | A WAVELET NEURAL NETWORK RAMWORK FOR SPEAKER IDNTIFCATION |
title_full_unstemmed | A WAVELET NEURAL NETWORK RAMWORK FOR SPEAKER IDNTIFCATION |
title_short | A WAVELET NEURAL NETWORK RAMWORK FOR SPEAKER IDNTIFCATION |
title_sort | wavelet neural network ramwork for speaker idntifcation |
url | https://www.joe.uobaghdad.edu.iq/index.php/main/article/view/2963 |
work_keys_str_mv | AT wamahmoud awaveletneuralnetworkramworkforspeakeridntifcation AT dhiadeenmsalih awaveletneuralnetworkramworkforspeakeridntifcation AT saleemmrtaha awaveletneuralnetworkramworkforspeakeridntifcation AT wamahmoud waveletneuralnetworkramworkforspeakeridntifcation AT dhiadeenmsalih waveletneuralnetworkramworkforspeakeridntifcation AT saleemmrtaha waveletneuralnetworkramworkforspeakeridntifcation |