99123 20230519145358.0 doi 10.1186/s13636-020-00191-3 sideral 122560 ART-2021-122560 eng Llombart, J. (orcid)0000-0002-9407-5817 Progressive loss functions for speech enhancement with deep neural networks 2021 Access copy available to the general public Unrestricted The progressive paradigm is a promising strategy to optimize network performance for speech enhancement purposes. Recent works have shown different strategies to improve the accuracy of speech enhancement solutions based on this mechanism. This paper studies the progressive speech enhancement using convolutional and residual neural network architectures and explores two criteria for loss function optimization: weighted and uniform progressive. This work carries out the evaluation on simulated and real speech samples with reverberation and added noise using REVERB and VoiceHome datasets. Experimental results show a variety of achievements among the loss function optimization criteria and the network architectures. Results show that the progressive design strengthens the model and increases the robustness to distortions due to reverberation and noise. info:eu-repo/semantics/openAccess by http://creativecommons.org/licenses/by/3.0/es/ 2.114 2021 ACOUSTICS 16 / 32 = 0.5 2021 Q2 T2 ENGINEERING, ELECTRICAL & ELECTRONIC 169 / 277 = 0.61 2021 Q3 T2 0.485 2021 Electrical and Electronic Engineering 2021 Q2 Acoustics and Ultrasonics 2021 Q2 2.9 2021 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Ribas, D. Universidad de Zaragoza (orcid)0000-0003-3813-4998 Miguel, A. Universidad de Zaragoza (orcid)0000-0001-5803-4316 Vicente, L. Universidad de Zaragoza (orcid)0000-0003-4391-5203 Ortega, A. Universidad de Zaragoza (orcid)0000-0002-3886-7748 Lleida, E. Universidad de Zaragoza (orcid)0000-0001-9137-4013 5008 800 Universidad de Zaragoza Dpto. Ingeniería Electrón.Com. Área Teoría Señal y Comunicac. 2021, 1 (2021), 1 [16 pp] EURASIP j. audio, speech music. process. EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING 1687-4714 971268 http://zaguan.unizar.es/record/99123/files/texto_completo.pdf Versión publicada 2751366 http://zaguan.unizar.es/record/99123/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:99123 articulos driver 2023-05-18-13:35:27 ARTICLE