000162513 001__ 162513
000162513 005__ 20251017144634.0
000162513 0247_ $$2doi$$a10.1109/ICASSP40776.2020.9053153
000162513 0248_ $$2sideral$$a129897
000162513 037__ $$aART-2020-129897
000162513 041__ $$aeng
000162513 100__ $$0(orcid)0000-0002-3505-0249$$aMingote, Victoria$$uUniversidad de Zaragoza
000162513 245__ $$aKnowledge Distillation and Random Erasing Data Augmentation for Text-Dependent Speaker Verification
000162513 260__ $$c2020
000162513 5060_ $$aAccess copy available to the general public$$fUnrestricted
000162513 5203_ $$aThis paper explores the Knowledge Distillation (KD) approach and a data augmentation technique to improve the generalization ability and robustness of text-dependent speaker verification (SV) systems. The KD method consists of two neural networks, known as Teacher and Student, where the student is trained to replicate the predictions from the teacher, so it learns their variability during the training process. To provide robustness to the distillation process, we apply Random Erasing (RE), a data augmentation technique which was created to improve the generalization ability of the neural networks. We have developed two alternatives of the combination of KD and RE, which, produce a more robust system with better performance, since the student network can learn from teacher predictions of data not existing in the original dataset. All alternatives were tested on RSR2015-Part I database, where the proposed variants outperform reference system based on a single network using RE.
000162513 536__ $$9info:eu-repo/grantAgreement/ES/DGA-FEDER/T36-17R$$9info:eu-repo/grantAgreement/ES/MINECO/TIN2017-85854-C4-1-R
000162513 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000162513 592__ $$a0.546$$b2020
000162513 593__ $$aElectrical and Electronic Engineering$$c2020
000162513 593__ $$aSoftware$$c2020
000162513 593__ $$aSignal Processing$$c2020
000162513 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000162513 700__ $$0(orcid)0000-0001-5803-4316$$aMiguel, Antonio$$uUniversidad de Zaragoza
000162513 700__ $$0(orcid)0000-0003-3813-4998$$aRibas, Dayana$$uUniversidad de Zaragoza
000162513 700__ $$0(orcid)0000-0002-3886-7748$$aOrtega, Alfonso$$uUniversidad de Zaragoza
000162513 700__ $$0(orcid)0000-0001-9137-4013$$aLleida, Eduardo$$uUniversidad de Zaragoza
000162513 7102_ $$15008$$2800$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Teoría Señal y Comunicac.
000162513 773__ $$g2020 (2020), 6824-6828$$tProceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing$$x0736-7791
000162513 8564_ $$s515021$$uhttps://zaguan.unizar.es/record/162513/files/texto_completo.pdf$$yPostprint
000162513 8564_ $$s2963105$$uhttps://zaguan.unizar.es/record/162513/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000162513 909CO $$ooai:zaguan.unizar.es:162513$$particulos$$pdriver
000162513 951__ $$a2025-10-17-14:28:14
000162513 980__ $$aARTICLE