Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.11889/2455
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hanani, Abualsoud | |
dc.contributor.author | Srouji, Fathi | |
dc.date.accessioned | 2016-10-13T05:28:16Z | |
dc.date.available | 2016-10-13T05:28:16Z | |
dc.date.issued | 2010 | |
dc.identifier.citation | en_US | |
dc.identifier.uri | http://hdl.handle.net/20.500.11889/2455 | |
dc.description | Srouji,Fathi: | en_US |
dc.description.abstract | One successful approach to language recognition is to focus on the most discriminative high level features of languages, such as phones and words. In this paper, we applied a similar approach to acoustic features using a single GMM-tokenizer followed by discriminatively trained language models. A feature selection technique based on the Support Vector Machine (SVM) is used to model higher order n-grams. Three different ways to build this tokenizer are explored and compared using discriminative uni-gram and generative GMM-UBM. A discriminative uni-gram using very large GMM tokenizer with 24,576 components yields an EER of 1.66%, rising to 0.71% when fused with other acoustic approaches, on the NIST‟03 LRE 30s evaluation | |
dc.language.iso | ar | en_US |
dc.publisher | معهد ماس | en_US |
dc.subject.lcsh | Translators (Computer programs) | |
dc.subject.lcsh | Computational linguistics | |
dc.subject.lcsh | Machine learning | |
dc.subject.lcsh | Gaussian processes | |
dc.subject.lcsh | Radar meteorology | |
dc.subject.lcsh | Weather forecasting | |
dc.title | Improved Language Recognition using Mixture Components Statistics | en_US |
dc.title.alternative | en_US | |
dc.type | Studies | en_US |
newfileds.department | en_US | |
newfileds.custom-issue-date | en_US | |
newfileds.corporate-author | en_US | |
newfileds.conference | en_US | |
newfileds.item-access-type | open_access | en_US |
newfileds.thesis-prog | en_US | |
newfileds.general-subject | Economics | en_US |
item.languageiso639-1 | other | - |
item.fulltext | With Fulltext | - |
item.grantfulltext | open | - |
Appears in Collections: | Fulltext Publications |
Page view(s)
130
Last Week
0
0
Last month
3
3
checked on Apr 14, 2024
Download(s)
46
checked on Apr 14, 2024
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.