Show simple item record

An Improved VTS Feature Compensation using Mixture Models of Distortion and IVN Training for Noisy Speech Recognition

contributor authorJun Du
contributor authorQiang Huo
date accessioned2020-03-13T00:15:04Z
date available2020-03-13T00:15:04Z
date issued2014
identifier issn2329-9290
identifier other6862902.pdf
identifier urihttps://libsearch.um.ac.ir:443/fum/handle/fum/1139828?show=full
formatgeneral
languageEnglish
publisherIEEE
titleAn Improved VTS Feature Compensation using Mixture Models of Distortion and IVN Training for Noisy Speech Recognition
typeJournal Paper
contenttypeMetadata Only
identifier padid8322093
subject keywordsGaussian processes
subject keywordshidden Markov models
subject keywordsleast mean squares methods
subject keywordsmaximum likelihood estimation
subject keywordsmixture models
subject keywordsseries (mathematics)
subject keywordsspeech recognition
subject keywordsAurora3 benchmark database
subject keywordsGaussian mixture component
subject keywordsIVN training
subject keywordsVTS feature compensation
subject keywordsacoustic modeling
subject keywordsadditive noise
subject keywordsconvolutional distortion
subject keywordsdistortion mixture model
subject keywordsdistortion model parameter
subject keywordshidden Markov model
subject keywordshigh order vector Taylor series approximation
subject keywordsin-vehicle connected digits recognition task
subject keywordsirrelevant varia
identifier doi10.1109/TASLP.2014.2341912
journal titleAudio, Speech, and Language Processing, IEEE/ACM Transactions on
journal volume22
journal issue11
filesize2327929
citations0


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record