Please use this identifier to cite or link to this item: https://idr.l4.nitk.ac.in/jspui/handle/123456789/7188
Full metadata record
DC FieldValueLanguage
dc.contributor.authorChittaragi, N.B.
dc.contributor.authorKoolagudi, S.G.
dc.date.accessioned2020-03-30T09:58:36Z-
dc.date.available2020-03-30T09:58:36Z-
dc.date.issued2018
dc.identifier.citation2017 10th International Conference on Contemporary Computing, IC3 2017, 2018, Vol.2018-January, , pp.1-6en_US
dc.identifier.urihttp://idr.nitk.ac.in/jspui/handle/123456789/7188-
dc.description.abstractIn this paper, word based dialect classification system is proposed by using acoustic characteristics of the speech signal. Dialects mainly represent the different pronunciation patterns of any language. Dialectal cues can exist at various levels such as phoneme, syllable, word, sentence and phrase in an utterance. Word level dialectal traits are extracted to recognize dialects since every word exhibits significant dialect discriminating cues. Intonational Variations in English (IViE) speech corpus recorded in British English has been considered. The corpus includes nine dialects which cover nine distinct regions of British Isles. Acoustic properties such as spectral and prosodic features are derived from word level to construct the feature vector. Further, two different classification algorithms such as support vector machine (SVM) and tree-based extreme gradient boosting (XGB) ensemble algorithms are used to extract the prominent patterns that are used to discriminate the dialects. From the experiments, a better performance has been observed with word level traits using ensemble methods over the SVM classification method. � 2017 IEEE.en_US
dc.titleAcoustic features based word level dialect classification using SVM and ensemble methodsen_US
dc.typeBook chapteren_US
Appears in Collections:2. Conference Papers

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.