Show simple item record

dc.contributor.authorSaraçlar, Murat
dc.contributor.authorDikici, Erinc
dc.contributor.authorArısoy, Ebru
dc.date.accessioned2019-02-28T13:04:26Z
dc.date.accessioned2019-02-28T11:08:16Z
dc.date.available2019-02-28T13:04:26Z
dc.date.available2019-02-28T11:08:16Z
dc.date.issued2015en_US
dc.identifier.citationSaraclar, M., Dikici, E., & Arisoy, E. (SEP 20-24, 2015). A Decade of Discriminative Language Modeling for Automatic Speech Recognition. 17th International Conference on Speech and Computer (SPECOM) Location: Athens, GREECE. 9319. p. 11-22.en_US
dc.identifier.issn0302-9743
dc.identifier.urihttp://dx.doi.org/10.1007/978-3-319-23132-7_2
dc.identifier.urihttps://hdl.handle.net/20.500.11779/648
dc.descriptionEbru Arısoy (MEF Author)en_US
dc.description##nofulltext##en_US
dc.description.abstractThis paper summarizes the research on discriminative language modeling focusing on its application to automatic speech recognition (ASR). A discriminative language model (DLM) is typically a linear or log-linear model consisting of a weight vector associated with a feature vector representation of a sentence. This flexible representation can include linguistically and statistically motivated features that incorporate morphological and syntactic information. At test time, DLMs are used to rerank the output of an ASR system, represented as an N-best list or lattice. During training, both negative and positive examples are used with the aim of directly optimizing the error rate. Various machine learning methods, including the structured perceptron, large margin methods and maximum regularized conditional log-likelihood, have been used for estimating the parameters of DLMs. Typically positive examples for DLM training come from the manual transcriptions of acoustic data while the negative examples are obtained by processing the same acoustic data with an ASR system. Recent research generalizes DLM training by either using automatic transcriptions for the positive examples or simulating the negative examples.en_US
dc.language.isoengen_US
dc.relation.ispartofConference: Speech And Computer (Specom 2015), 17th International Conference on Speech and Computer (SPECOM) Location: Athens, GREECE Date: SEP 20-24, 2015en_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAutomatic Speech Recognitionen_US
dc.subjectDiscriminative Trainingen_US
dc.subjectLanguage Modelingen_US
dc.titleA decade of discriminative language modeling for automatic speech recognitionen_US
dc.typeconferenceObjecten_US
dc.departmentMühendislik Fakültesi, Elektrik Elektronik Mühendisliği Bölümüen_US
dc.authoridEbru Arısoy / 0000-0002-8311-3611en_US
dc.identifier.volume9319en_US
dc.identifier.startpage11en_US
dc.identifier.endpage22en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.description.wosidWOS:000365866300002en_US
dc.description.scopusid2-s2.0-84945969170en_US
dc.contributor.institutionauthorArısoy, Ebru
dc.description.woscitationindexConference Proceedings Citation Index- Scienceen_US
dc.identifier.wosqualityQ4en_US
dc.description.WoSDocumentTypeProceedings Paperen_US
dc.description.WoSPublishedMonthEylülen_US
dc.description.WoSIndexDate2015en_US
dc.description.WoSYOKperiodYÖK - 2015-16en_US
dc.identifier.doi10.1007/978-3-319-23132-7_2en_US
dc.identifier.scopusqualityQ3en_US


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