000110869 001__ 110869
000110869 005__ 20240319080949.0
000110869 0247_ $$2doi$$a10.3390/app12041832
000110869 0248_ $$2sideral$$a127693
000110869 037__ $$aART-2022-127693
000110869 041__ $$aeng
000110869 100__ $$0(orcid)0000-0002-3142-0708$$aGimeno, P.$$uUniversidad de Zaragoza
000110869 245__ $$aUnsupervised adaptation of deep speech activity detection models to unseen domains
000110869 260__ $$c2022
000110869 5060_ $$aAccess copy available to the general public$$fUnrestricted
000110869 5203_ $$aSpeech Activity Detection (SAD) aims to accurately classify audio fragments containing human speech. Current state-of-the-art systems for the SAD task are mainly based on deep learning solutions. These applications usually show a significant drop in performance when test data are different from training data due to the domain shift observed. Furthermore, machine learning algorithms require large amounts of labelled data, which may be hard to obtain in real applications. Considering both ideas, in this paper we evaluate three unsupervised domain adaptation techniques applied to the SAD task. A baseline system is trained on a combination of data from different domains and then adapted to a new unseen domain, namely, data from Apollo space missions coming from the Fearless Steps Challenge. Experimental results demonstrate that domain adaptation techniques seeking to minimise the statistical distribution shift provide the most promising results. In particular, Deep CORAL method reports a 13% relative improvement in the original evaluation metric when compared to the unadapted baseline model. Further experiments show that the cascaded application of Deep CORAL and pseudo-labelling techniques can improve even more the results, yielding a significant 24% relative improvement in the evaluation metric when compared to the baseline system.
000110869 536__ $$9info:eu-repo/grantAgreement/ES/AEI/PDC2021-120846-C41$$9info:eu-repo/grantAgreement/ES/DGA/T36-20R$$9info:eu-repo/grantAgreement/EC/H2020/101007666/EU/Exchanges for SPEech ReseArch aNd TechnOlogies/ESPERANTO$$9This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 101007666-ESPERANTO$$9info:eu-repo/grantAgreement/ES/MCIN/AEI/10.13039/501100011033
000110869 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000110869 590__ $$a2.7$$b2022
000110869 592__ $$a0.492$$b2022
000110869 591__ $$aPHYSICS, APPLIED$$b78 / 160 = 0.488$$c2022$$dQ2$$eT2
000110869 591__ $$aENGINEERING, MULTIDISCIPLINARY$$b42 / 90 = 0.467$$c2022$$dQ2$$eT2
000110869 591__ $$aCHEMISTRY, MULTIDISCIPLINARY$$b100 / 178 = 0.562$$c2022$$dQ3$$eT2
000110869 591__ $$aMATERIALS SCIENCE, MULTIDISCIPLINARY$$b208 / 343 = 0.606$$c2022$$dQ3$$eT2
000110869 593__ $$aFluid Flow and Transfer Processes$$c2022$$dQ2
000110869 593__ $$aMaterials Science (miscellaneous)$$c2022$$dQ2
000110869 593__ $$aEngineering (miscellaneous)$$c2022$$dQ2
000110869 593__ $$aInstrumentation$$c2022$$dQ2
000110869 593__ $$aProcess Chemistry and Technology$$c2022$$dQ3
000110869 593__ $$aComputer Science Applications$$c2022$$dQ3
000110869 594__ $$a4.5$$b2022
000110869 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000110869 700__ $$0(orcid)0000-0003-3813-4998$$aRibas, D.
000110869 700__ $$0(orcid)0000-0002-3886-7748$$aOrtega, A.$$uUniversidad de Zaragoza
000110869 700__ $$0(orcid)0000-0001-5803-4316$$aMiguel, A.$$uUniversidad de Zaragoza
000110869 700__ $$0(orcid)0000-0001-9137-4013$$aLleida, E.$$uUniversidad de Zaragoza
000110869 7102_ $$15008$$2800$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Teoría Señal y Comunicac.
000110869 773__ $$g12, 4 (2022), 1832 [23 pp.]$$pAppl. sci.$$tApplied Sciences (Switzerland)$$x2076-3417
000110869 8564_ $$s1282345$$uhttps://zaguan.unizar.es/record/110869/files/texto_completo.pdf$$yVersión publicada
000110869 8564_ $$s2927232$$uhttps://zaguan.unizar.es/record/110869/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000110869 909CO $$ooai:zaguan.unizar.es:110869$$particulos$$pdriver
000110869 951__ $$a2024-03-18-12:52:19
000110869 980__ $$aARTICLE