Speaker Verification Using Autoregressive Spectrum of Speech Signal in Composite Vector Stochastic Processes Model Representation

Show simple item record

dc.contributor.author Chmelařová, Natalija cze
dc.contributor.author Tykhonov, Vyacheslav A. cze
dc.contributor.author Bezruk, Valerij M. cze
dc.contributor.author Chmelař, Pavel cze
dc.contributor.author Rejfek, Luboš cze
dc.date.accessioned 2020-03-19T13:22:44Z
dc.date.available 2020-03-19T13:22:44Z
dc.date.issued 2019 eng
dc.identifier.issn 2454-7190 eng
dc.identifier.uri https://hdl.handle.net/10195/75177
dc.description.abstract This paper deals with the speaker verification system similar to a fingerprint or an eye scanner. For these purpose a long-term words' model and its spectral characteristics were used. The speaker verification method uses the word's sound parametric spectrum factorization in composite vector stochastic process representation based on the multiplicative autoregressive model. The developed method enables to receive the words' features with stable characteristics for the same speaker and differ for different speakers. During the training phase speaker's etalon frequencies has to be estimated for a pronounced word repeated several times. In the verification phase a speaker pronouncing the same word, word's frequencies are estimated and compared with the etalon frequencies database to find the best match or his deny. The results presented in the paper showed the high correct identification probability. eng
dc.format p. 178-190 eng
dc.language.iso eng eng
dc.publisher Institute of Mechanics of Continua and Mathematical Sciences eng
dc.relation.ispartof Journal of Mechanics of Continua and Mathematical Sciences, volume No. 4, issue: 11 2019 eng
dc.rights Práce není přístupná eng
dc.subject Composite Vector Stochastic Processes Autoregressive Models eng
dc.subject Power Spectrum Density eng
dc.subject Speaker Verification eng
dc.subject Composite Vector Stochastic Processes Autoregressive Models cze
dc.subject Power Spectrum Density cze
dc.subject Speaker Verification cze
dc.title Speaker Verification Using Autoregressive Spectrum of Speech Signal in Composite Vector Stochastic Processes Model Representation eng
dc.title.alternative Speaker Verification Using Autoregressive Spectrum of Speech Signal in Composite Vector Stochastic Processes Model Representation cze
dc.type article eng
dc.description.abstract-translated This paper deals with the speaker verification system similar to a fingerprint or an eye scanner. For these purpose a long-term words' model and its spectral characteristics were used. The speaker verification method uses the word's sound parametric spectrum factorization in composite vector stochastic process representation based on the multiplicative autoregressive model. The developed method enables to receive the words' features with stable characteristics for the same speaker and differ for different speakers. During the training phase speaker's etalon frequencies has to be estimated for a pronounced word repeated several times. In the verification phase a speaker pronouncing the same word, word's frequencies are estimated and compared with the etalon frequencies database to find the best match or his deny. The results presented in the paper showed the high correct identification probability. cze
dc.peerreviewed yes eng
dc.publicationstatus postprint eng
dc.identifier.doi 10.26782/jmcms.spl.4/2019.11.00018 eng
dc.relation.publisherversion http://www.journalimcms.org/special_issue/speaker-verification-using-autoregressive-spectrum-of-speech-signal-in-composite-vector-stochastic-processes-model-representation/ eng
dc.project.ID SGS_2019_021/Výzkum pokročilých metod modelování, simulace, řízení, databázových systémů a webových aplikací eng
dc.identifier.wos 000495435200018 eng
dc.identifier.obd 39883779 eng


This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account