Please use this identifier to cite or link to this item:
http://ricaxcan.uaz.edu.mx/jspui/handle/20.500.11845/1727
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor | 31249 | es_ES |
dc.contributor.other | https://orcid.org/0000-0002-7337-8974 | - |
dc.contributor.other | https://orcid.org/0000-0002-8060-6170 | - |
dc.coverage.spatial | Global | es_ES |
dc.creator | Becerra, Aldonso | - |
dc.creator | De la Rosa Vargas, José Ismael | - |
dc.creator | González Ramírez, Efrén | - |
dc.creator | Pedroza, David | - |
dc.creator | Escalante, Iracemi | - |
dc.creator | Santos, Eduardo | - |
dc.date.accessioned | 2020-04-17T20:02:33Z | - |
dc.date.available | 2020-04-17T20:02:33Z | - |
dc.date.issued | 2020-03 | - |
dc.identifier | info:eu-repo/semantics/publishedVersion | es_ES |
dc.identifier.issn | 1380-7501 | es_ES |
dc.identifier.issn | 1573-7721 | es_ES |
dc.identifier.uri | http://ricaxcan.uaz.edu.mx/jspui/handle/20.500.11845/1727 | - |
dc.identifier.uri | https://doi.org/10.48779/crw1-0409 | - |
dc.description.abstract | Training procedures of a deep neural network are still an area with ample research possibilities and constant improvement either to increase its efficiency or its time performance. One of the lesser-addressed components is its objective function, which is an underlying aspect to consider when there is the necessity to achieve better error rates in the area of automatic speech recognition. The aim of this paper is to present two new variations of the frame-level cost function for training a deep neural network with the purpose of obtaining superior word error rates in speech recognition applied to a case study in Spanish. | es_ES |
dc.language.iso | eng | es_ES |
dc.publisher | Springer | es_ES |
dc.relation | https://doi.org/10.1007/s11042-020-08782-0 | es_ES |
dc.relation.uri | generalPublic | es_ES |
dc.rights | Atribución-NoComercial-SinDerivadas 3.0 Estados Unidos de América | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/us/ | * |
dc.source | Multimedia Tools Applications, Vol. 79 / 80, marzo 2020 | es_ES |
dc.subject.classification | INGENIERIA Y TECNOLOGIA [7] | es_ES |
dc.subject.other | Speech recognition | es_ES |
dc.subject.other | Neural networks | es_ES |
dc.subject.other | Deep learning | es_ES |
dc.subject.other | Machine learning | es_ES |
dc.subject.other | Cross-entropy | es_ES |
dc.subject.other | Frame-level loss function | es_ES |
dc.title | A comparative case study of neural network training by using frame-level cost functions for automatic speech recognition purposes in Spanish | es_ES |
dc.type | info:eu-repo/semantics/article | es_ES |
Appears in Collections: | *Documentos Académicos*-- M. en Ciencias del Proc. de la Info. |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
31_Becerra_DelaRosa MTAP P1 2020.pdf | Becerra_DelaRosa MTAP 2020 | 175,61 kB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License