Using an Ensemble of Classifiers for Mispronunciation Feedback
2011 (English)In: Proceedings of SLaTE / [ed] Strik, H.; Delmonte, R.; Russel, M., Venice, Italy, 2011Conference paper, Published paper (Refereed)
Abstract [en]
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. Instead of providing feedback at every mispronounced phoneme, the method attempts toprovide feedback about typical mispronunciations by a certain student, over an entire session of several utterances. Two case studies that demonstrate how the paradigm is applied to provide suitable feedback to two students is also described in this pape
Place, publisher, year, edition, pages
Venice, Italy, 2011.
National Category
Computer Sciences Language Technology (Computational Linguistics)
Identifiers
URN: urn:nbn:se:kth:diva-52238Scopus ID: 2-s2.0-84944325677OAI: oai:DiVA.org:kth-52238DiVA, id: diva2:465534
Conference
SLaTE, 24-26 August 2011, Venice, Italy
Note
tmh_import_11_12_14.
QC 20111220
2011-12-142011-12-142024-03-18Bibliographically approved