Afficher la notice abrégée

dc.contributor.authorMartín Doñas, Juan M.
dc.contributor.authorGómez García, Ángel Manuel 
dc.contributor.authorGonzález López, José Andrés 
dc.contributor.authorPeinado Herreros, Antonio Miguel 
dc.date.accessioned2021-11-15T07:28:13Z
dc.date.available2021-11-15T07:28:13Z
dc.date.issued2018-09-19
dc.identifier.citationMartín-Doñas, J. M., Gomez, A. M., Gonzalez, J. A., & Peinado, A. M. (2018). A deep learning loss function based on the perceptual evaluation of the speech quality. IEEE Signal processing letters, 25(11), 1680-1684.es_ES
dc.identifier.urihttp://hdl.handle.net/10481/71497
dc.description.abstractThis letter proposes a perceptual metric for speech quality evaluation, which is suitable, as a loss function, for training deep learning methods. This metric, derived from the perceptual evaluation of the speech quality algorithm, is computed in a per-frame basis and from the power spectra of the reference and processed speech signal. Thus, two disturbance terms, which account for distortion once auditory masking and threshold effects are factored in, amend the mean square error (MSE) loss function by introducing perceptual criteria based on human psychoacoustics. The proposed loss function is evaluated for noisy speech enhancement with deep neural networks. Experimental results show that our metric achieves significant gains in speech quality (evaluated using an objective metric and a listening test) when compared to using MSE or other perceptual-based loss functions from the literature.es_ES
dc.description.sponsorshipSpanish MINECO/FEDER (Grant Number: TEC2016-80141-P)es_ES
dc.description.sponsorshipSpanish Ministry of Education through the National Program FPU (Grant Number: FPU15/04161)es_ES
dc.description.sponsorshipNVIDIA Corporation with the donation of a Titan X GPUes_ES
dc.language.isoenges_ES
dc.publisherIEEEes_ES
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 España*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subjectDeep learning (DL)es_ES
dc.subjectSpeech enhancementes_ES
dc.titleA Deep Learning Loss Function Based on the Perceptual Evaluation of the Speech Qualityes_ES
dc.typejournal articlees_ES
dc.rights.accessRightsopen accesses_ES
dc.identifier.doi10.1109/LSP.2018.2871419


Fichier(s) constituant ce document

[PDF]

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée

Atribución-NoComercial-SinDerivadas 3.0 España
Excepté là où spécifié autrement, la license de ce document est décrite en tant que Atribución-NoComercial-SinDerivadas 3.0 España