148271 20250117145309.0 doi 10.1109/LSP.2021.3084501 sideral 126436 ART-2021-126436 eng Gimeno, P Universidad de Zaragoza (orcid)0000-0002-3142-0708 Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data 2021 Access copy available to the general public Unrestricted Area under the ROC curve (AUC) optimisation techniques developed for neural networks have recently demonstrated their capabilities in different audio and speech related tasks. However, due to its intrinsic nature, AUC optimisation has focused only on binary tasks so far. In this paper, we introduce an extension to the AUC optimisation framework so that it can be easily applied to an arbitrary number of classes, aiming to overcome the issues derived from training data limitations in deep learning solutions. Building upon the multiclass definitions of the AUC metric found in the literature, we define two new training objectives using a one-versus-one and a one-versus-rest approach. In order to demonstrate its potential, we apply them in an audio segmentation task with limited training data that aims to differentiate 3 classes: foreground music, background music and no music. Experimental results show that our proposal can improve the performance of audio segmentation systems significantly compared to traditional training criteria such as cross entropy. info:eu-repo/grantAgreement/ES/DGA/T36-20R info:eu-repo/grantAgreement/EC/H2020/101007666/EU/Exchanges for SPEech ReseArch aNd TechnOlogies/ESPERANTO This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 101007666-ESPERANTO 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/ 3.201 2021 ENGINEERING, ELECTRICAL & ELECTRONIC 113 / 274 = 0.412 2021 Q2 T2 1.361 2021 Electrical and Electronic Engineering 2021 Q1 Applied Mathematics 2021 Q1 6.6 2021 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Mingote, V Universidad de Zaragoza (orcid)0000-0002-3505-0249 Ortega, A Universidad de Zaragoza (orcid)0000-0002-3886-7748 Miguel, A Universidad de Zaragoza (orcid)0000-0001-5803-4316 Lleida, E Universidad de Zaragoza (orcid)0000-0001-9137-4013 5008 800 Universidad de Zaragoza Dpto. Ingeniería Electrón.Com. Área Teoría Señal y Comunicac. 28 (2021), 1135-1139 IEEE signal process. lett. IEEE SIGNAL PROCESSING LETTERS 1070-9908 429490 http://zaguan.unizar.es/record/148271/files/texto_completo.pdf Postprint 3234155 http://zaguan.unizar.es/record/148271/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:148271 articulos driver 2025-01-17-14:45:03 ARTICLE