Matches in SemOpenAlex for { <https://semopenalex.org/work/W2942393092> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2942393092 endingPage "52608" @default.
- W2942393092 startingPage "52589" @default.
- W2942393092 abstract "Computer-assisted language learning (CALL) systems provide an automated framework to identify mispronunciation and give useful feedback. Traditionally, handcrafted acoustic-phonetic features are used to detect mispronunciation. From this line of research, this paper investigates the use of the deep convolutional neural network for mispronunciation detection of Arabic phonemes. We propose two methods with different techniques, i.e., convolutional neural network features (CNN_Features)-based technique and a transfer learning-based technique to detect mispronunciation detection. In the first method, we use deep CNN features to detect mispronunciation. We also extract features from different layers of CNN (layer4 to layer7) to train k-nearest neighbor (KNN), support vector machine (SVM), and neural network (NN) classifiers. In the transfer learning-based method, we trained the CNN using transfer learning to detect mispronunciation. To evaluate the performance of the system, we compare the results of these methods with baseline handcrafted features-based method for 28 Arabic phonemes. In the baseline method, we use the same classifiers; KNN, SVM, and NN to detect mispronunciation. The experimental results show that handcrafted_features method, CNN_features, and transfer learning-based method achieve an accuracy of 82%, 91.7%, and 92.2%, respectively. The performance analysis shows that transfer learning-based method outperforms handcrafted_features and transfer CNN_features-based methods and achieve an accuracy of 92.2%. The proposed transfer learning-based method also outperforms the state-of-art techniques in term of accuracy." @default.
- W2942393092 created "2019-05-03" @default.
- W2942393092 creator A5020654281 @default.
- W2942393092 creator A5035993905 @default.
- W2942393092 creator A5044779375 @default.
- W2942393092 creator A5063552634 @default.
- W2942393092 date "2019-01-01" @default.
- W2942393092 modified "2023-10-06" @default.
- W2942393092 title "Mispronunciation Detection Using Deep Convolutional Neural Network Features and Transfer Learning-Based Model for Arabic Phonemes" @default.
- W2942393092 cites W1970870811 @default.
- W2942393092 cites W1975615230 @default.
- W2942393092 cites W2008834750 @default.
- W2942393092 cites W2031438579 @default.
- W2942393092 cites W2044465660 @default.
- W2942393092 cites W2070133242 @default.
- W2942393092 cites W2091856355 @default.
- W2942393092 cites W2097180381 @default.
- W2942393092 cites W2106051978 @default.
- W2942393092 cites W2110215948 @default.
- W2942393092 cites W2114492809 @default.
- W2942393092 cites W2128838222 @default.
- W2942393092 cites W2130640900 @default.
- W2942393092 cites W2134124280 @default.
- W2942393092 cites W2137469438 @default.
- W2942393092 cites W2139008940 @default.
- W2942393092 cites W2152334841 @default.
- W2942393092 cites W2552635739 @default.
- W2942393092 cites W2590223281 @default.
- W2942393092 cites W2750793847 @default.
- W2942393092 cites W2811065464 @default.
- W2942393092 cites W4292023222 @default.
- W2942393092 doi "https://doi.org/10.1109/access.2019.2912648" @default.
- W2942393092 hasPublicationYear "2019" @default.
- W2942393092 type Work @default.
- W2942393092 sameAs 2942393092 @default.
- W2942393092 citedByCount "29" @default.
- W2942393092 countsByYear W29423930922019 @default.
- W2942393092 countsByYear W29423930922020 @default.
- W2942393092 countsByYear W29423930922021 @default.
- W2942393092 countsByYear W29423930922022 @default.
- W2942393092 countsByYear W29423930922023 @default.
- W2942393092 crossrefType "journal-article" @default.
- W2942393092 hasAuthorship W2942393092A5020654281 @default.
- W2942393092 hasAuthorship W2942393092A5035993905 @default.
- W2942393092 hasAuthorship W2942393092A5044779375 @default.
- W2942393092 hasAuthorship W2942393092A5063552634 @default.
- W2942393092 hasBestOaLocation W29423930921 @default.
- W2942393092 hasConcept C108583219 @default.
- W2942393092 hasConcept C119857082 @default.
- W2942393092 hasConcept C12267149 @default.
- W2942393092 hasConcept C150899416 @default.
- W2942393092 hasConcept C153180895 @default.
- W2942393092 hasConcept C154945302 @default.
- W2942393092 hasConcept C28490314 @default.
- W2942393092 hasConcept C41008148 @default.
- W2942393092 hasConcept C50644808 @default.
- W2942393092 hasConcept C81363708 @default.
- W2942393092 hasConceptScore W2942393092C108583219 @default.
- W2942393092 hasConceptScore W2942393092C119857082 @default.
- W2942393092 hasConceptScore W2942393092C12267149 @default.
- W2942393092 hasConceptScore W2942393092C150899416 @default.
- W2942393092 hasConceptScore W2942393092C153180895 @default.
- W2942393092 hasConceptScore W2942393092C154945302 @default.
- W2942393092 hasConceptScore W2942393092C28490314 @default.
- W2942393092 hasConceptScore W2942393092C41008148 @default.
- W2942393092 hasConceptScore W2942393092C50644808 @default.
- W2942393092 hasConceptScore W2942393092C81363708 @default.
- W2942393092 hasLocation W29423930921 @default.
- W2942393092 hasOpenAccess W2942393092 @default.
- W2942393092 hasPrimaryLocation W29423930921 @default.
- W2942393092 hasRelatedWork W2996856019 @default.
- W2942393092 hasRelatedWork W3012459282 @default.
- W2942393092 hasRelatedWork W3018421652 @default.
- W2942393092 hasRelatedWork W3021430260 @default.
- W2942393092 hasRelatedWork W3091976719 @default.
- W2942393092 hasRelatedWork W3192840557 @default.
- W2942393092 hasRelatedWork W4220996320 @default.
- W2942393092 hasRelatedWork W4285149559 @default.
- W2942393092 hasRelatedWork W4312200629 @default.
- W2942393092 hasRelatedWork W4382286161 @default.
- W2942393092 hasVolume "7" @default.
- W2942393092 isParatext "false" @default.
- W2942393092 isRetracted "false" @default.
- W2942393092 magId "2942393092" @default.
- W2942393092 workType "article" @default.