Genetic algorithms/decision tree hybrid based approach for speaker verification system

The performance of a speaker recognizer like the speaker verifier strongly depends on the input feature. The feature set has to be both highly discriminative and compact to get a good performance. This study aims to introduce a new approach of feature extraction specifically designed for Speaker Ver...

Full description

Saved in:
Bibliographic Details
Main Author: Vela, Josie T.
Format: text
Language:English
Published: Animo Repository 2005
Subjects:
Online Access:https://animorepository.dlsu.edu.ph/etd_masteral/3246
https://animorepository.dlsu.edu.ph/context/etd_masteral/article/10084/viewcontent/CDTG003824_P.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: De La Salle University
Language: English
id oai:animorepository.dlsu.edu.ph:etd_masteral-10084
record_format eprints
spelling oai:animorepository.dlsu.edu.ph:etd_masteral-100842023-05-29T09:51:21Z Genetic algorithms/decision tree hybrid based approach for speaker verification system Vela, Josie T. The performance of a speaker recognizer like the speaker verifier strongly depends on the input feature. The feature set has to be both highly discriminative and compact to get a good performance. This study aims to introduce a new approach of feature extraction specifically designed for Speaker Verification System. The feasibility of using a Genetic Algorithms/Decision Tree (GA/DT) hybrid approach to choose from the original MFCC (Mel-Frequency Cepstral Coefficient) data the set of feature vectors that appropriately represents personal speech characteristics of a speaker is investigated. The GA is used to evolve selected feature vectors and the decision tree (DT) algorithm is used to evaluate the fitness functions of the chromosomes (feature sets) evolved by the GA. Moreover, it evaluates and compares, in terms of speed and accuracy, the performance of the Speaker Verification System (SVS) using the General Approach and the SVS with the GA/DT Hybrid Approach. There are two (2) sets of data used in the experiments, namely, the clean data taken from the TIMIT database that is provided in the SPEAR database of CSLU and the unclean data taken from real life recordings of the speakers that deal with constant background noise. For the clean data, the performance of the two (2) systems and the existing work are all compared in terms of accuracy. The results show that the performance of the two systems is comparable with the existing work. Moreover, the SVS w/ the GA/DT hybrid approach performs better than the General Approach in terms of accuracy and speed. On the other hand, for the unclean data, the experimental results show that the SVS with the GA/DT hybrid approach performs better than the General Approach in terms of accuracy and speed but the results obtained is not as good as using a clean data. We still think that this is a good result though since we are able to find out that the idea we put in our proposed model worked. Perhaps in the future our proposed model would be improved further. 2005-03-01T08:00:00Z text application/pdf https://animorepository.dlsu.edu.ph/etd_masteral/3246 https://animorepository.dlsu.edu.ph/context/etd_masteral/article/10084/viewcontent/CDTG003824_P.pdf Master's Theses English Animo Repository Genetic algorithms Combinatorial optimization Expert systems (Computer science)--Verification Automatic speech recognition Speech processing systems. Computer Sciences
institution De La Salle University
building De La Salle University Library
continent Asia
country Philippines
Philippines
content_provider De La Salle University Library
collection DLSU Institutional Repository
language English
topic Genetic algorithms
Combinatorial optimization
Expert systems (Computer science)--Verification
Automatic speech recognition
Speech processing systems.
Computer Sciences
spellingShingle Genetic algorithms
Combinatorial optimization
Expert systems (Computer science)--Verification
Automatic speech recognition
Speech processing systems.
Computer Sciences
Vela, Josie T.
Genetic algorithms/decision tree hybrid based approach for speaker verification system
description The performance of a speaker recognizer like the speaker verifier strongly depends on the input feature. The feature set has to be both highly discriminative and compact to get a good performance. This study aims to introduce a new approach of feature extraction specifically designed for Speaker Verification System. The feasibility of using a Genetic Algorithms/Decision Tree (GA/DT) hybrid approach to choose from the original MFCC (Mel-Frequency Cepstral Coefficient) data the set of feature vectors that appropriately represents personal speech characteristics of a speaker is investigated. The GA is used to evolve selected feature vectors and the decision tree (DT) algorithm is used to evaluate the fitness functions of the chromosomes (feature sets) evolved by the GA. Moreover, it evaluates and compares, in terms of speed and accuracy, the performance of the Speaker Verification System (SVS) using the General Approach and the SVS with the GA/DT Hybrid Approach. There are two (2) sets of data used in the experiments, namely, the clean data taken from the TIMIT database that is provided in the SPEAR database of CSLU and the unclean data taken from real life recordings of the speakers that deal with constant background noise. For the clean data, the performance of the two (2) systems and the existing work are all compared in terms of accuracy. The results show that the performance of the two systems is comparable with the existing work. Moreover, the SVS w/ the GA/DT hybrid approach performs better than the General Approach in terms of accuracy and speed. On the other hand, for the unclean data, the experimental results show that the SVS with the GA/DT hybrid approach performs better than the General Approach in terms of accuracy and speed but the results obtained is not as good as using a clean data. We still think that this is a good result though since we are able to find out that the idea we put in our proposed model worked. Perhaps in the future our proposed model would be improved further.
format text
author Vela, Josie T.
author_facet Vela, Josie T.
author_sort Vela, Josie T.
title Genetic algorithms/decision tree hybrid based approach for speaker verification system
title_short Genetic algorithms/decision tree hybrid based approach for speaker verification system
title_full Genetic algorithms/decision tree hybrid based approach for speaker verification system
title_fullStr Genetic algorithms/decision tree hybrid based approach for speaker verification system
title_full_unstemmed Genetic algorithms/decision tree hybrid based approach for speaker verification system
title_sort genetic algorithms/decision tree hybrid based approach for speaker verification system
publisher Animo Repository
publishDate 2005
url https://animorepository.dlsu.edu.ph/etd_masteral/3246
https://animorepository.dlsu.edu.ph/context/etd_masteral/article/10084/viewcontent/CDTG003824_P.pdf
_version_ 1768028936273395712