Please use this identifier to cite or link to this item: http://archives.univ-biskra.dz/handle/123456789/4274
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAbdelghani Harrag-
dc.contributor.authorD. Saigaa-
dc.contributor.authorA. Bouchelaghem-
dc.contributor.authorM. Drif-
dc.contributor.authorS. Zeghlache-
dc.contributor.authorN. Harrag-
dc.date.accessioned2014-11-25T08:46:13Z-
dc.date.available2014-11-25T08:46:13Z-
dc.date.issued2014-11-25-
dc.identifier.urihttp://archives.univ-biskra.dz/handle/123456789/4274-
dc.description.abstractThis paper addresses the feature subset selection for an automatic Arabic speaker recognition system. An effective algorithm based on genetic algorithm is proposed for discovering the best feature combinations using feature reduction and recognition error rate as performance measure. Experimentation is carried out using QSDAS corpora. The results of experiments indicate that, with the optimized feature subset, the performance of the system is improved. Moreover, the speed of recognition is significantly increased, number of features is reduced over 60% which consequently decrease the complexity of our ASR systemen_US
dc.language.isoenen_US
dc.subjectgenetic algorithm; feature selection; speaker recognition.en_US
dc.titleHow to Reduce Dimension while Improving Performanceen_US
dc.typeArticleen_US
Appears in Collections:Publications Internationales

Files in This Item:
File Description SizeFormat 
“How to Reduce Dimension while Improving Performance.pdf461,03 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.