Grapheme-Based Cross-Language Forced Alignment: Results with Uralic Languages

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorLeinonen, Juhoen_US
dc.contributor.authorVirpioja, Samien_US
dc.contributor.authorKurimo, Mikkoen_US
dc.contributor.departmentDepartment of Signal Processing and Acousticsen
dc.contributor.groupauthorSpeech Recognitionen
dc.date.accessioned2021-12-15T07:23:57Z
dc.date.available2021-12-15T07:23:57Z
dc.date.issued2021-05-01en_US
dc.description.abstractForced alignment is an effective process to speed up linguistic research. However, most forced aligners are language-dependent, and under-resourced languages rarely have enough resources to train an acoustic model for an aligner. We present a new Finnish grapheme-based forced aligner and demonstrate its performance by aligning multiple Uralic languages and English as an unrelated language. We show that even a simple non-expert created grapheme-to-phoneme mapping can result in useful word alignments.en
dc.description.versionPeer revieweden
dc.format.extent6
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationLeinonen, J, Virpioja, S & Kurimo, M 2021, Grapheme-Based Cross-Language Forced Alignment: Results with Uralic Languages. in Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa). Linköping Electronic Conference Proceedings, no. 178, NEALT Proceedings Series, vol. 45, Linköping University Electronic Press, pp. 345-350, Nordic Conference on Computational Linguistics, Reykjavik, Iceland, 31/05/2021. < https://www.aclweb.org/anthology/2021.nodalida-main.36.pdf >en
dc.identifier.isbn978-91-7929-614-8
dc.identifier.issn1650-3740
dc.identifier.issn1650-3686
dc.identifier.issn1736-8197
dc.identifier.issn1736-6305
dc.identifier.otherPURE UUID: 9fb2969c-b9ed-41d9-b498-04dac4a4bd10en_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/9fb2969c-b9ed-41d9-b498-04dac4a4bd10en_US
dc.identifier.otherPURE LINK: https://ep.liu.se/konferensnummer.aspx?series=ecp&issue=178
dc.identifier.otherPURE LINK: https://www.aclweb.org/anthology/2021.nodalida-main.36.pdfen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/76625050/2021.nodalida_main.36_2.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/111615
dc.identifier.urnURN:NBN:fi:aalto-2021121510756
dc.language.isoenen
dc.relation.ispartofNordic Conference on Computational Linguisticsen
dc.relation.ispartofseriesProceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)en
dc.relation.ispartofseriespp. 345-350en
dc.relation.ispartofseriesLinköping Electronic Conference Proceedings ; 178en
dc.relation.ispartofseriesNEALT Proceedings Series ; Volume 45en
dc.rightsopenAccessen
dc.titleGrapheme-Based Cross-Language Forced Alignment: Results with Uralic Languagesen
dc.typeA4 Artikkeli konferenssijulkaisussafi
dc.type.versionpublishedVersion

Files