Please use this identifier to cite or link to this item: https://dspace.upt.ro/xmlui/handle/123456789/3839
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMunteanu, Doru-
dc.contributor.authorOancea, Eugeniu-
dc.date.accessioned2021-09-14T09:00:51Z-
dc.date.available2021-09-14T09:00:51Z-
dc.date.issued2004-
dc.identifier.citationMunteanu, Doru. Romanian language robust continuous speech recognition. Timişoara: Editura Politehnica, 2004en_US
dc.identifier.urihttp://primo.upt.ro:1701/primo-explore/search?query=any,contains,Romanian%20language%20robust%20continuous%20speech%20recognition&tab=default_tab&search_scope=40TUT&vid=40TUT_V1&lang=ro_RO&offset=0 Link Primo-
dc.description.abstractIn this paper we present some principles for continuous speech recognition, insisting on the influence of several environmental factors that could affect recognition performances. A Romanian language recognizer has been trained using both context dependent and context independent models. Multistyle training strategy was used to train the recognizer with various levels of artificial noise added on the clean speech. Experimental results prove that this scheme strongly increase the system robustness to additive noise.en_US
dc.language.isoenen_US
dc.publisherTimişoara : Editura Politehnicaen_US
dc.relation.ispartofseriesBuletinul ştiinţific al Universităţii „Politehnica” din Timişoara, România. Seria electronică şi telecomunicaţii, Tom 49(63), fasc. 1 (2004), p. 301-304-
dc.subjectContinuous speech recognitionen_US
dc.subjectEnvironmental robustnessen_US
dc.subjectMultistyle trainingen_US
dc.titleRomanian language robust continuous speech recognition [articol]en_US
dc.typeArticleen_US
Appears in Collections:Articole științifice/Scientific articles

Files in This Item:
File Description SizeFormat 
BUPT_ART_Munteanu_f.pdf550 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.