Publication:
Deep Maxout Networks applied to Noise-Robust Speech Recognition

Simple item page
dc.affiliation.dptoUC3M. Departamento de Teoría de la Señal y Comunicacioneses
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Procesado Multimediaes
dc.contributor.authorCalle Silos, Fernando de laes
dc.contributor.authorGallardo Antolín, Ascensiónes
dc.contributor.authorPeláez Moreno, Carmenes
dc.date.accessioned2015-09-04T11:08:55Z
dc.date.issued2014
dc.descriptionProceedings of: IberSPEECH 2014 "VIII Jornadas en Tecnologías del Habla" and "IV Iberian SLTech Workshop". Las Palmas de Gran Canaria, Spain, November 19-21, 2014.en
dc.description.abstractDeep Neural Networks (DNN) have become very popular for acoustic modeling due to the improvements found over traditional Gaussian Mixture Models (GMM). However, not many works have addressed the robustness of these systems under noisy conditions. Recently, the machine learning community has proposed new methods to improve the accuracy of DNNs by using techniques such as dropout and maxout. In this paper, we investigate Deep Maxout Networks (DMN) for acoustic modeling in a noisy automatic speech recognition environment. Experiments show that DMNs improve substantially the recognition accuracy over DNNs and other traditional techniques in both clean and noisy conditions on the TIMIT dataset.en
dc.description.sponsorshipThis contribution has been supported by an Airbus Defense and Space Grant (Open Innovation - SAVIER) and Spanish Government-CICYT project 2011-26807/TEC.en
dc.description.statusPublicadoes
dc.format.extent10
dc.format.mimetypeapplication/pdf
dc.identifier.bibliographicCitationNavarro Mesa, J. L., et al. (eds.) (2014). Advances in Speech and Language Technologies for Iberian Languages: Second International Conference, IberSPEECH 2014, Las Palmas de Gran Canaria, Spain, November 19-21, 2014. Proceedings. (pp. 109-118). (Lecture Notes in Computer Science; 8854). Springer International Publishing.es
dc.identifier.doi10.1007/978-3-319-13623-3_12
dc.identifier.isbn978-3-319-13622-6 (print)
dc.identifier.isbn978-3-319-13623-3 (online)
dc.identifier.issn0302-9743 (print)
dc.identifier.issn1611-3349 (online)
dc.identifier.publicationfirstpage109
dc.identifier.publicationlastpage118
dc.identifier.publicationtitleAdvances in Speech and Language Technologies for Iberian Languages: Second International Conference, IberSPEECH 2014, Las Palmas de Gran Canaria, Spain, November 19-21, 2014. Proceedings.en
dc.identifier.urihttps://hdl.handle.net/10016/21528
dc.identifier.uxxiCC/0000022425
dc.language.isoengen
dc.publisherSpringeren
dc.relation.eventdateNovember 19-21, 2014.en
dc.relation.eventplaceLas Palmas de Gran Canaria, Spainen
dc.relation.eventtitleIberSPEECH 2014 "VIII Jornadas en Tecnologías del Habla" and "IV Iberian SLTech Workshop"es
dc.relation.ispartofseriesLecture Notes in Computer Scienceen
dc.relation.ispartofseries8854
dc.relation.projectIDGobierno de España. TEC2011–26807es
dc.relation.publisherversionhttp://dx.doi.org/10.1007/978-3-319-13623-3_12en
dc.rights© 2014 Springer International Publishing Switzerlanden
dc.rights.accessRightsopen accessen
dc.subject.ecienciaTelecomunicacioneses
dc.subject.otherNoise robustnessen
dc.subject.otherDeep neural networksen
dc.subject.otherDropouten
dc.subject.otherDeep maxout networksen
dc.subject.otherSpeech recognitionen
dc.subject.otherDeep learningen
dc.titleDeep Maxout Networks applied to Noise-Robust Speech Recognitionen
dc.typeconference paper*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
deep_IberSPEECH_2014_ps.pdf
Size:
1.24 MB
Format:
Adobe Portable Document Format
Download
Collections
DTSC - GPM - Comunicaciones en congresos y otros eventos
DTSC - GPM - Capítulos de Monografías