Character-based units for Unlimited Vocabulary Continuous Speech Recognition

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.author Smit, Peter
dc.contributor.author Gangireddy, Siva
dc.contributor.author Enarvi, Seppo
dc.contributor.author Virpioja, Sami
dc.contributor.author Kurimo, Mikko
dc.date.accessioned 2018-02-09T10:05:14Z
dc.date.available 2018-02-09T10:05:14Z
dc.date.issued 2018
dc.identifier.citation Smit , P , Gangireddy , S , Enarvi , S , Virpioja , S & Kurimo , M 2017 , Character-based units for Unlimited Vocabulary Continuous Speech Recognition . in Automatic Speech Recognition and Understanding (ASRU), IEEE Workshop on . IEEE , pp. 149-154 . en
dc.identifier.other PURE UUID: bf94112f-8c70-453d-ad69-021ccdd56e25
dc.identifier.other PURE ITEMURL: https://research.aalto.fi/en/publications/characterbased-units-for-unlimited-vocabulary-continuous-speech-recognition(bf94112f-8c70-453d-ad69-021ccdd56e25).html
dc.identifier.other PURE FILEURL: https://research.aalto.fi/files/15224133/smit2017chars.pdf
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/29968
dc.description.abstract We study character-based language models in the state-of-the-art speech recognition framework. This approach has advantages over both word-based systems and so-called end-to-end ASR systems that do not have separate acoustic and language models. We describe the necessary modifications needed to build an effective character-based ASR system using the Kaldi toolkit and evaluate the models based on words, statistical morphs, and characters for both Finnish and Arabic. The morph-based models yield the best recognition results for both well-resourced and lower-resourced tasks, but the character-based models are close to their performance in the lower-resource tasks, outperforming the word-based models. Character-based models are especially good at predicting novel word forms that were not seen in the training data. Using character-based neural network language models is both computationally efficient and provides a larger gain compared to the morph and word-based systems. en
dc.format.extent 149-154
dc.format.mimetype application/pdf
dc.language.iso en en
dc.relation.ispartofseries Automatic Speech Recognition and Understanding (ASRU), IEEE Workshop on en
dc.rights openAccess en
dc.subject.other 113 Computer and information sciences en
dc.title Character-based units for Unlimited Vocabulary Continuous Speech Recognition en
dc.type A4 Artikkeli konferenssijulkaisussa fi
dc.description.version Peer reviewed en
dc.contributor.department Department of Signal Processing and Acoustics
dc.subject.keyword 113 Computer and information sciences
dc.identifier.urn URN:NBN:fi:aalto-201802091465
dc.identifier.doi 10.1109/ASRU.2017.8268929
dc.type.version acceptedVersion


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search archive


Advanced Search

article-iconSubmit a publication

Browse

My Account