Publication: Deep Maxout Networks applied to Noise-Robust Speech Recognition
dc.affiliation.dpto | UC3M. Departamento de Teoría de la Señal y Comunicaciones | es |
dc.affiliation.grupoinv | UC3M. Grupo de Investigación: Procesado Multimedia | es |
dc.contributor.author | Calle Silos, Fernando de la | es |
dc.contributor.author | Gallardo Antolín, Ascensión | es |
dc.contributor.author | Peláez Moreno, Carmen | es |
dc.date.accessioned | 2015-09-04T11:08:55Z | |
dc.date.issued | 2014 | |
dc.description | Proceedings 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.abstract | Deep 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.sponsorship | This 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.status | Publicado | es |
dc.format.extent | 10 | |
dc.format.mimetype | application/pdf | |
dc.identifier.bibliographicCitation | Navarro 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.doi | 10.1007/978-3-319-13623-3_12 | |
dc.identifier.isbn | 978-3-319-13622-6 (print) | |
dc.identifier.isbn | 978-3-319-13623-3 (online) | |
dc.identifier.issn | 0302-9743 (print) | |
dc.identifier.issn | 1611-3349 (online) | |
dc.identifier.publicationfirstpage | 109 | |
dc.identifier.publicationlastpage | 118 | |
dc.identifier.publicationtitle | 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. | en |
dc.identifier.uri | https://hdl.handle.net/10016/21528 | |
dc.identifier.uxxi | CC/0000022425 | |
dc.language.iso | eng | en |
dc.publisher | Springer | en |
dc.relation.eventdate | November 19-21, 2014. | en |
dc.relation.eventplace | Las Palmas de Gran Canaria, Spain | en |
dc.relation.eventtitle | IberSPEECH 2014 "VIII Jornadas en Tecnologías del Habla" and "IV Iberian SLTech Workshop" | es |
dc.relation.ispartofseries | Lecture Notes in Computer Science | en |
dc.relation.ispartofseries | 8854 | |
dc.relation.projectID | Gobierno de España. TEC2011–26807 | es |
dc.relation.publisherversion | http://dx.doi.org/10.1007/978-3-319-13623-3_12 | en |
dc.rights | © 2014 Springer International Publishing Switzerland | en |
dc.rights.accessRights | open access | en |
dc.subject.eciencia | Telecomunicaciones | es |
dc.subject.other | Noise robustness | en |
dc.subject.other | Deep neural networks | en |
dc.subject.other | Dropout | en |
dc.subject.other | Deep maxout networks | en |
dc.subject.other | Speech recognition | en |
dc.subject.other | Deep learning | en |
dc.title | Deep Maxout Networks applied to Noise-Robust Speech Recognition | en |
dc.type | conference paper | * |
dc.type.hasVersion | AM | * |
dspace.entity.type | Publication |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- deep_IberSPEECH_2014_ps.pdf
- Size:
- 1.24 MB
- Format:
- Adobe Portable Document Format