Please use this identifier to cite or link to this item: http://ricaxcan.uaz.edu.mx/jspui/handle/20.500.11845/1886
Full metadata record
DC FieldValueLanguage
dc.contributor31249es_ES
dc.contributor.otherhttps://orcid.org/0000-0002-7337-8974-
dc.contributor.otherhttps://orcid.org/0000-0002-8060-6170-
dc.coverage.spatialGlobales_ES
dc.creatorBecerra de la Rosa, Aldonso-
dc.creatorDe la Rosa Vargas, José Ismael-
dc.creatorGonzález Ramírez, Efrén-
dc.date.accessioned2020-05-06T19:51:43Z-
dc.date.available2020-05-06T19:51:43Z-
dc.date.issued2016-10-
dc.identifierinfo:eu-repo/semantics/publishedVersiones_ES
dc.identifier.urihttp://ricaxcan.uaz.edu.mx/jspui/handle/20.500.11845/1886-
dc.identifier.urihttps://doi.org/10.48779/xc36-yn86-
dc.description.abstractThe aim of this paper is to exhibit a comparative case study of the conventional speech recognition GMM-HMM (Gaussian mixture model - hidden Markov model) architecture and the recent model based on deep neural networks. During years the GMM approach has controlled the speech recognition tasks, however it has been surpassed with the resurgence of artificial neural networks. To exemplify these acoustic modeling frameworks, a case study has been conducted by using the Kaldi toolkit, employing a personalized speaker-independent mid-vocabulary voice corpus for recognition of digit strings and personal name lists in latin spanish on a connected-words pone dialing task. The speech recognition accuracy obtained in the results shows a better word error rate by using the DNN acoustic modeling. A 20:71% relative improvement is obtained with DNNHMM models (3:33% WER) in respect to the lowest GMM-HMM rate (4:20% WER).es_ES
dc.language.isoenges_ES
dc.publisherIEEEes_ES
dc.relation.urigeneralPublices_ES
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 Estados Unidos de América*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/*
dc.sourceProc. of the IEEE Andean Council International Conference - IEEE ANDESCON 2016, at Arequipa, Perú, pp. 1-4, 2016.es_ES
dc.subject.classificationINGENIERIA Y TECNOLOGIA [7]es_ES
dc.subject.otherSpeech recognitiones_ES
dc.subject.otherGMM-HMMes_ES
dc.subject.otherDNN-HMMes_ES
dc.titleA Case Study of Speech Recognition in Spanish: from Conventional to Deep Approaches_ES
dc.typeinfo:eu-repo/semantics/conferencePaperes_ES
Appears in Collections:*Documentos Académicos*-- M. en Ciencias del Proc. de la Info.

Files in This Item:
File Description SizeFormat 
64_Becerra_DelaRosa_IEEEANDESCON P1 2016.pdfBecerra_DelaRosa_IEEEANDESCON P1 2016405,7 kBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons