Detecting confusable phoneme pairs for Swedish language learners depending on their first language
2011 (English)In: TMH-QPSR, Vol. 51, no 1, 89-92 p.Article in journal (Other academic) Published
This paper proposes a paradigm where commonly made segmental pronunciation errors are modeled as pair-wise confusions between two or more phonemes in the language that is being learnt. The method uses an ensemble of support vector machine classiﬁers with time varying Mel frequency cepstral features to distinguish between several pairs of phonemes. These classiﬁers are then applied to classify the phonemes uttered by second language learners. Using this method, an assessment is made regarding the typical pronunciation problems that students learning Swedish would encounter, depending on their ﬁrst language.
Place, publisher, year, edition, pages
2011. Vol. 51, no 1, 89-92 p.
Computer Science Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:kth:diva-52217OAI: oai:DiVA.org:kth-52217DiVA: diva2:465513
tmh_import_11_12_14. QC 20111220. QC 201201112011-12-142011-12-142012-01-11Bibliographically approved