Show simple item record

dc.contributor.authorLiu, Xen
dc.contributor.authorGales, Marken
dc.contributor.authorWoodland, Philipen
dc.date.accessioned2014-07-17T11:24:50Z
dc.date.available2014-07-17T11:24:50Z
dc.date.issued2013-05-26en
dc.identifier.citationIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2013, 8421 - 8425. DOI: 10.1109/ICASSP.2013.6639308
dc.identifier.issn1520-6149
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/245536
dc.description.abstractIn natural languages multiple word sequences can represent the same underlying meaning. Only modelling the observed surface word sequence can result in poor context coverage, for example, when using n-gram language models (LM). To handle this issue, paraphrastic LMs were proposed in previous research and successfully applied to a US English conversational telephone speech transcription task. In order to exploit the complementary characteristics of paraphrastic LMs and neural network LMs (NNLM), the combination between the two is investigated in this paper. To investigate paraphrastic LMs’ generalization ability to other languages, experiments are conducted on a Mandarin Chinese broadcast speech transcription task. Using a paraphrastic multi-level LM modelling both word and phrase sequences, significant error rate reductions of 0.9% absolute (9% relative) and 0.5% absolute (5% relative) were obtained over the baseline n-gram and NNLM systems respectively, after a combination with word and phrase level NNLMs.
dc.description.sponsorshipThe research leading to these results was supported by EPSRC Programme Grant EP/I031022/1 (Natural Speech Technology)
dc.languageEnglishen
dc.language.isoenen
dc.rightsDSpace@Cambridge license
dc.subjectlanguage modelen
dc.subjectparaphraseen
dc.subjectspeech recognitionen
dc.titleParaphrastic language models and combination with neural network language modelsen
dc.typeArticle
dc.description.versionThis is the author accepted manuscript. The final version is available at http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6639308.en
prism.endingPage8425
prism.publicationDate2013en
prism.publicationNameIEEE ICASSP2013en
prism.startingPage8421
dc.rioxxterms.funderEPSRC
dc.rioxxterms.projectidEP/I031022/1
rioxxterms.versionofrecord10.1109/ICASSP.2013.6639308en
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2013-05-26en
dc.contributor.orcidGales, Mark [0000-0002-5311-8219]
dc.contributor.orcidWoodland, Philip [0000-0001-9069-0225]
rioxxterms.typeJournal Article/Reviewen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record