{"title":"Text independent automatic speaker recognition using selforganizing maps","authors":"A.T. Mafra, M. Simões","doi":"10.1109/IAS.2004.1348670","DOIUrl":null,"url":null,"abstract":"This work presents one implementation of an automatic speaker recognition system, based on selforganizing map (SOM) neural networks. The voice of each speaker is modeled by a SOM, trained to specialize in the quantization of feature vectors (MFCCs) extracted from his voice. When a test sample is presented, it is quantized by all SpMs, that compete for the speaker: the SOM with smallest quantization error defines the speaker. The system was tested on a speaker identification task over a 14 speaker set, with phrases from three phonetically balanced sets and one variable answer set. The results comprovate the method's efficiency.","PeriodicalId":131410,"journal":{"name":"Conference Record of the 2004 IEEE Industry Applications Conference, 2004. 39th IAS Annual Meeting.","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Conference Record of the 2004 IEEE Industry Applications Conference, 2004. 39th IAS Annual Meeting.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IAS.2004.1348670","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9
Abstract
This work presents one implementation of an automatic speaker recognition system, based on selforganizing map (SOM) neural networks. The voice of each speaker is modeled by a SOM, trained to specialize in the quantization of feature vectors (MFCCs) extracted from his voice. When a test sample is presented, it is quantized by all SpMs, that compete for the speaker: the SOM with smallest quantization error defines the speaker. The system was tested on a speaker identification task over a 14 speaker set, with phrases from three phonetically balanced sets and one variable answer set. The results comprovate the method's efficiency.