Browse

Automatic Pronunciation Assessment of Korean Spoken by L2 Learners Using Best Feature Set Selection

Cited 0 time in Web of Science Cited 2 time in Scopus
Authors
Ryu, Hyuksu; Hong, Hyejin; Kim, Sunhee; Chung, Minhwa
Issue Date
2016-12-16
Publisher
Asia-Pacific Signal and Information Processing Association (APSIPA)
the Institute of Electrical and Electronis Engineers, Inc.
Citation
2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), Jeju, 2016, pp. 1-6
Keywords
computer aided instructionfeature selectionlinguisticsnatural languagesprincipal component analysisregression analysisspeech recognitionBSSChinese languageEnglish languageJapanese languageKorean language learnerL2 Korean Speech CorpusL2 learnersMongolian languagePCRRussian languageautomatic pronunciation assessmentbest feature set selectionfeature selectionlearner speech forced-alignmentlearner speech recognitionmultiple linear regressionnative Korean acoustic modelnative languageprincipal component regressionpronunciation scoresalient featuresspeech segmentspoken Korean languageAcousticsComputational modelingCorrelationFeature extractionManualsSpeechSpeech recognition
Abstract
This paper proposes a method for automatic pronunciation assessment of Korean spoken by L2 learners by selecting the best feature set from a collection of the most well-known features in the literature. The L2 Korean Speech Corpus is used for assessment modeling, where the native languages of the L2 learners are English, Chinese, Japanese, Russian, and Mongolian. In our system, learners speech is forced-aligned and recognized using a native Korean acoustic model. Based on these results, various features for pronunciation assessment are computed, and divided into four categories such as RATE, SEGMENT, SILENCE, and GOP. Pronunciation scores produced by combining categories of features by multiple linear regression are used as a baseline. In order to enhance the baseline performance, relevant features are selected by using Principal Component Regression (PCR) and Best Subset Selection (BSS), respectively. The results show that the BSS model outperforms the baseline and the PCR model, and that features corresponding to speech segment and rate are selected as the relevant ones for automatic pronunciation assessment. The observed tendency of salient features will be useful for further improvement of automatic pronunciation assessment model for Korean language learners.
Language
English
URI
https://hdl.handle.net/10371/117487
DOI
https://doi.org/10.1109/APSIPA.2016.7820673
Files in This Item:
Appears in Collections:
College of Humanities (인문대학)Linguistics (언어학과)Journal Papers (저널논문_언어학과)
  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse