Change search
ReferencesLink to record
Permanent link

Direct link
A web-deployed Swedish spoken CALL systembased on a large shared English/Swedish feature grammar
University of Geneva, Switzerland.
University of Geneva, Switzerland.
University of Geneva, Switzerland.
University of Geneva, Switzerland.
Show others and affiliations
2012 (English)In: Proceedings of the SLTC 2012 workshop on NLP for CALL / [ed] Lars Borin and Elena Volodina, Linköping University Electronic Press, 2012, 37-46 p.Conference paper (Refereed)
Place, publisher, year, edition, pages
Linköping University Electronic Press, 2012. 37-46 p.
Linköping Electronic Conference Proceedings, ISSN 1650-3686 (print), 1650-3740 (online) ; 80
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-86155OAI: diva2:575274
SLTC 2012 workshop on NLP for CALL, 25 October 2012, Lund, Sweden

We describe a Swedish version of CALL-SLT,a web-deployed CALL system that allows beginner/intermediate students to practise generativespoken language skills. Speech recognitionis grammar-based, with language modelsderived, using the Regulus platform, fromsubstantial domain-independent feature grammars.The paper focusses on the Swedishgrammar resources, which were developedby generalising the existing English featuregrammar into a shared grammar for Englishand Swedish. It turns out that this can be donevery economically: all but a handful of rulesand features are shared, and English grammaressentially ends up being treated as a reducedform of Swedish. We conclude by presentinga simple evaluation which compares theSwedish and French versions of CALL-SLT.

Available from: 2012-12-18 Created: 2012-12-08 Last updated: 2015-09-22Bibliographically approved

Open Access in DiVA

fulltext(249 kB)108 downloads
File information
File name FULLTEXT01.pdfFile size 249 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Conference websiteWorkshop on NLP for CALL

Search in DiVA

By author/editor
Eklund, RobertJönsson, ArneMcAllister, Anita
By organisation
Language and CultureFaculty of Arts and SciencesDepartment of Computer and Information ScienceThe Institute of TechnologySpeech and Language PathologyFaculty of Health SciencesDepartment of Otorhinolaryngology in Linköping
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 108 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 150 hits
ReferencesLink to record
Permanent link

Direct link