Show simple item record

dc.contributor.authorHernández-Abrego, G
dc.contributor.authorMariño Acebal, José Bernardo
dc.date.accessioned2017-04-27T17:15:42Z
dc.date.available2017-04-27T17:15:42Z
dc.date.issued2000
dc.identifier.citationHernández-Abrego, G., Mariño, J.B. Contextual confidence measures for continuous speech recognition. A: IEEE International Conference on Acoustics, Speech, and Signal Processing. "ICASSP 2000: 2000 IEEE international conference on acoustics, speech, and signal processing: silver anniversary, proceedings: 5-9 June 2000: Hilton Hotel and Convention Center, Istanbul, Turkey". Istanbul: Institute of Electrical and Electronics Engineers (IEEE), 2000, p. 1803-1086.
dc.identifier.isbn0-7803-6293-4
dc.identifier.urihttp://hdl.handle.net/2117/103809
dc.description.abstractThis paper explores the repercussion of contextual information into confidence measuring for continuous speech recognition results. Our approach comprises three steps: to extract confidence predictors out of recognition results, to compile those predictors into confidence measures by means of a fuzzy inference system whose parameters have been estimated, directly from examples, with an evolutionary strategy and, finally, to upgrade the confidence measures by the inclusion of contextual information. Through experimentation with two different continuous speech application tasks, results show that the context re-scoring procedure improves the capabilities of confidence measures to discriminate between correct and incorrect recognition results for every level of thresholding, even when a rather simple method to add contextual information is considered.
dc.format.extent-716 p.
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació
dc.subject.lcshTelecommunication
dc.subject.otherPrediction theory
dc.subject.otherSpeech recognition
dc.subject.otherParameter estimation
dc.subject.otherFuzzy systems
dc.titleContextual confidence measures for continuous speech recognition
dc.typeConference report
dc.subject.lemacTelecomunicació
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.identifier.doi10.1109/ICASSP.2000.862104
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://ieeexplore.ieee.org/document/862104/
dc.rights.accessOpen Access
local.identifier.drac2375729
dc.description.versionPostprint (published version)
local.citation.authorHernández-Abrego, G.; Mariño, J.B.
local.citation.contributorIEEE International Conference on Acoustics, Speech, and Signal Processing
local.citation.pubplaceIstanbul
local.citation.publicationNameICASSP 2000: 2000 IEEE international conference on acoustics, speech, and signal processing: silver anniversary, proceedings: 5-9 June 2000: Hilton Hotel and Convention Center, Istanbul, Turkey
local.citation.startingPage1803
local.citation.endingPage1086


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder