000086322 001__ 86322
000086322 005__ 20230914083238.0
000086322 0247_ $$2doi$$a10.3390/app9163295
000086322 0248_ $$2sideral$$a114978
000086322 037__ $$aART-2019-114978
000086322 041__ $$aeng
000086322 100__ $$0(orcid)0000-0002-3505-0249$$aMingote, Victoria$$uUniversidad de Zaragoza
000086322 245__ $$aSupervector extraction for encoding speaker and phrase information with neural networks for text-dependent speaker verification
000086322 260__ $$c2019
000086322 5060_ $$aAccess copy available to the general public$$fUnrestricted
000086322 5203_ $$aIn this paper, we propose a new differentiable neural network with an alignment mechanism for text-dependent speaker verification. Unlike previous works, we do not extract the embedding of an utterance from the global average pooling of the temporal dimension. Our system replaces this reduction mechanism by a phonetic phrase alignment model to keep the temporal structure of each phrase since the phonetic information is relevant in the verification task. Moreover, we can apply a convolutional neural network as front-end, and, thanks to the alignment process being differentiable, we can train the network to produce a supervector for each utterance that will be discriminative to the speaker and the phrase simultaneously. This choice has the advantage that the supervector encodes the phrase and speaker information providing good performance in text-dependent speaker verification tasks. The verification process is performed using a basic similarity metric. The new model using alignment to produce supervectors was evaluated on the RSR2015-Part I database, providing competitive results compared to similar size networks that make use of the global average pooling to extract embeddings. Furthermore, we also evaluated this proposal on the RSR2015-Part II. To our knowledge, this system achieves the best published results obtained on this second part.
000086322 536__ $$9info:eu-repo/grantAgreement/ES/DGA-FEDER/T36-17R$$9info:eu-repo/grantAgreement/ES/MINECO/TIN2017-85854-C4-1-R
000086322 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000086322 590__ $$a2.474$$b2019
000086322 591__ $$aPHYSICS, APPLIED$$b62 / 154 = 0.403$$c2019$$dQ2$$eT2
000086322 591__ $$aENGINEERING, MULTIDISCIPLINARY$$b32 / 91 = 0.352$$c2019$$dQ2$$eT2
000086322 591__ $$aCHEMISTRY, MULTIDISCIPLINARY$$b88 / 176 = 0.5$$c2019$$dQ2$$eT2
000086322 591__ $$aMATERIALS SCIENCE, MULTIDISCIPLINARY$$b161 / 314 = 0.513$$c2019$$dQ3$$eT2
000086322 592__ $$a0.418$$b2019
000086322 593__ $$aEngineering (miscellaneous)$$c2019$$dQ1
000086322 593__ $$aFluid Flow and Transfer Processes$$c2019$$dQ2
000086322 593__ $$aProcess Chemistry and Technology$$c2019$$dQ2
000086322 593__ $$aInstrumentation$$c2019$$dQ2
000086322 593__ $$aMaterials Science (miscellaneous)$$c2019$$dQ2
000086322 593__ $$aComputer Science Applications$$c2019$$dQ3
000086322 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000086322 700__ $$0(orcid)0000-0001-5803-4316$$aMiguel, Antonio$$uUniversidad de Zaragoza
000086322 700__ $$0(orcid)0000-0002-3886-7748$$aOrtega, Alfonso$$uUniversidad de Zaragoza
000086322 700__ $$0(orcid)0000-0001-9137-4013$$aLleida, Eduardo$$uUniversidad de Zaragoza
000086322 7102_ $$15008$$2800$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Teoría Señal y Comunicac.
000086322 773__ $$g9, 16 (2019), 3295 [12 pp.]$$pAppl. sci.$$tApplied Sciences (Switzerland)$$x2076-3417
000086322 8564_ $$s1144341$$uhttps://zaguan.unizar.es/record/86322/files/texto_completo.pdf$$yVersión publicada
000086322 8564_ $$s108636$$uhttps://zaguan.unizar.es/record/86322/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000086322 909CO $$ooai:zaguan.unizar.es:86322$$particulos$$pdriver
000086322 951__ $$a2023-09-13-10:46:50
000086322 980__ $$aARTICLE