162513 20251017144634.0 doi 10.1109/ICASSP40776.2020.9053153 sideral 129897 ART-2020-129897 eng Mingote, Victoria Universidad de Zaragoza (orcid)0000-0002-3505-0249 Knowledge Distillation and Random Erasing Data Augmentation for Text-Dependent Speaker Verification 2020 Access copy available to the general public Unrestricted This 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. info:eu-repo/grantAgreement/ES/DGA-FEDER/T36-17R info:eu-repo/grantAgreement/ES/MINECO/TIN2017-85854-C4-1-R info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ 0.546 2020 Electrical and Electronic Engineering 2020 Software 2020 Signal Processing 2020 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Miguel, Antonio Universidad de Zaragoza (orcid)0000-0001-5803-4316 Ribas, Dayana Universidad de Zaragoza (orcid)0000-0003-3813-4998 Ortega, Alfonso Universidad de Zaragoza (orcid)0000-0002-3886-7748 Lleida, Eduardo Universidad de Zaragoza (orcid)0000-0001-9137-4013 5008 800 Universidad de Zaragoza Dpto. Ingeniería Electrón.Com. Área Teoría Señal y Comunicac. 2020 (2020), 6824-6828 Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing 0736-7791 515021 http://zaguan.unizar.es/record/162513/files/texto_completo.pdf Postprint 2963105 http://zaguan.unizar.es/record/162513/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:162513 articulos driver 2025-10-17-14:28:14 ARTICLE