File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Use of voicing features in HMM-based speech recognition

TitleUse of voicing features in HMM-based speech recognition
Authors
KeywordsAutocorrelation Function
Cepstral Mean Subtraction
Discriminative Training
Hidden Markov Models
Hierarchical Signal Bias Removal
Jitter
Periodicity
Speech Recognition Features
Voiced And Unvoiced Speech
Voicing
Issue Date2002
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/specom
Citation
Speech Communication, 2002, v. 37 n. 3-4, p. 197-211 How to Cite?
AbstractWe investigate speech recognition features related to voicing functions that indicate whether the vocal folds are vibrating. We describe two voicing features, periodicity and jitter, and demonstrate that they are powerful voicing discriminators. The periodicity and jitter features and their first and second time derivatives are appended to a standard 38-dimensional feature vector comprising the first and second time derivatives of the frame energy and the cepstral coefficients with their first and second time derivatives. HMM-based connected-digit (CD) and large-vocabulary (LV) recognition experiments comparing the traditional and extended feature sets show that voicing features and spectral information are complementary and that improved speech recognition performance is obtained by combining the two sources of information. We further conclude that the difference in performance with and without voicing becomes more significant when minimum string error (MSE) training is used than when maximum likelihood (ML) training is used. © 2002 Elsevier Science B.V. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/178772
ISSN
2015 Impact Factor: 1.038
2015 SCImago Journal Rankings: 0.685
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorThomson, DLen_US
dc.contributor.authorChengalvarayan, Ren_US
dc.date.accessioned2012-12-19T09:49:39Z-
dc.date.available2012-12-19T09:49:39Z-
dc.date.issued2002en_US
dc.identifier.citationSpeech Communication, 2002, v. 37 n. 3-4, p. 197-211en_US
dc.identifier.issn0167-6393en_US
dc.identifier.urihttp://hdl.handle.net/10722/178772-
dc.description.abstractWe investigate speech recognition features related to voicing functions that indicate whether the vocal folds are vibrating. We describe two voicing features, periodicity and jitter, and demonstrate that they are powerful voicing discriminators. The periodicity and jitter features and their first and second time derivatives are appended to a standard 38-dimensional feature vector comprising the first and second time derivatives of the frame energy and the cepstral coefficients with their first and second time derivatives. HMM-based connected-digit (CD) and large-vocabulary (LV) recognition experiments comparing the traditional and extended feature sets show that voicing features and spectral information are complementary and that improved speech recognition performance is obtained by combining the two sources of information. We further conclude that the difference in performance with and without voicing becomes more significant when minimum string error (MSE) training is used than when maximum likelihood (ML) training is used. © 2002 Elsevier Science B.V. All rights reserved.en_US
dc.languageengen_US
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/specomen_US
dc.relation.ispartofSpeech Communicationen_US
dc.subjectAutocorrelation Functionen_US
dc.subjectCepstral Mean Subtractionen_US
dc.subjectDiscriminative Trainingen_US
dc.subjectHidden Markov Modelsen_US
dc.subjectHierarchical Signal Bias Removalen_US
dc.subjectJitteren_US
dc.subjectPeriodicityen_US
dc.subjectSpeech Recognition Featuresen_US
dc.subjectVoiced And Unvoiced Speechen_US
dc.subjectVoicingen_US
dc.titleUse of voicing features in HMM-based speech recognitionen_US
dc.typeArticleen_US
dc.identifier.emailThomson, DL: dthomson@hku.hken_US
dc.identifier.authorityThomson, DL=rp00788en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1016/S0167-6393(01)00011-5en_US
dc.identifier.scopuseid_2-s2.0-0036642777en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-0036642777&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume37en_US
dc.identifier.issue3-4en_US
dc.identifier.spage197en_US
dc.identifier.epage211en_US
dc.identifier.isiWOS:000176314600003-
dc.publisher.placeNetherlandsen_US
dc.identifier.scopusauthoridThomson, DL=7202586830en_US
dc.identifier.scopusauthoridChengalvarayan, R=6701843465en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats