{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T04:05:42Z","timestamp":1750910742165,"version":"3.41.0"},"reference-count":50,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2017]]},"DOI":"10.1587\/transinf.2017edp7019","type":"journal-article","created":{"date-parts":[[2017,8,31]],"date-time":"2017-08-31T22:27:32Z","timestamp":1504218452000},"page":"2174-2182","source":"Crossref","is-referenced-by-count":12,"title":["Articulatory Modeling for Pronunciation Error Detection without Non-Native Training Data Based on DNN Transfer Learning"],"prefix":"10.1587","volume":"E100.D","author":[{"given":"Richeng","family":"DUAN","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Kyoto University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"KAWAHARA","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masatake","family":"DANTSUJI","sequence":"additional","affiliation":[{"name":"Academic Center for Computing and Media Studies, Kyoto University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinsong","family":"ZHANG","sequence":"additional","affiliation":[{"name":"School of Information Science, Beijing Language and Culture University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] C. Cucchiarini, F.D. Wet, H. Strik, and L. Boves, \u201cAssessment of Dutch pronunciation by means of automatic speech recognition technology,\u201d Proc. ICSLP, pp.1739-1742, 1998."},{"key":"2","unstructured":"[2] C.-H. Jo, T. Kawahara, S. Doshita, and M. Dantsuji, \u201cAutomatic Pronunciation Error Detection and Guidance for Foreign Language Learning,\u201d Proc. ICSLP, pp.2639-2642, 1998."},{"key":"3","unstructured":"[3] W. Menzel, D. Herron, P. Bonaventura, and R. Morton, \u201cAutomatic detection and correction of non-native English pronunciations,\u201d Proc. Speech Technology in Language Learning, pp.49-56, 2000."},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] A. Neri, C. Cucchiarini, H. Strik, and L. Boves, \u201cThe pedagogy technology interface in computer assisted pronunciation training,\u201d Proc. Computer assisted language learning, pp.441-467, 2002.","DOI":"10.1076\/call.15.5.441.13473"},{"key":"5","unstructured":"[5] S. Seneff, C. Wang, and J. Zhang, \u201cSpoken conversational interaction for language learning,\u201d Proc. InSTIL\/ICALL Symposiumon on Computer Assisted Learning, pp.151-154, 2004."},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] R. Downey, H. Farhady, R. Present-Thomas, M. Suzukiet, and M. Van, \u201cEvaluation of the usefulness of the Versant for English Test: A response,\u201d Proc. Language Assessment Quarterly, pp.160-167, 2008.","DOI":"10.1080\/15434300801934744"},{"key":"7","unstructured":"[7] H. Strik, J. Colpaert, J. Doremalen, and C. Cucchiarini, \u201cThe DISCO ASR-based CALL system: practicing L2 oral skills and beyond,\u201d Proc. International Conference on Language Resources and Evaluation, Istanbul, pp.2702-2707, 2012."},{"key":"8","unstructured":"[8] X. Qian, H. Meng, and F. Soong, \u201cA Two-Pass Framework of Mispronunciation Detection and Diagnosis for Computer-Aided Pronunciation Training,\u201d Proc. IEEE\/ACM Trans. Audio, Speech, Language Process., 24(6), pp.1020-1028, 2016."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] H. Franco, L. Neumeyer, M. Ramos, and H. Bratt, \u201cAutomatic detection of phone-level mispronunciation for language learning,\u201d Proc. Eurospeech, vol.2, pp.851-854, 1999.","DOI":"10.21437\/Eurospeech.1999-207"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] S. Witt and S. Young, \u201cPhone-level pronunciation scoring and assessment for interactive language learning,\u201d Proc. Speech Communication, vol.30, pp.95-108, 2000.","DOI":"10.1016\/S0167-6393(99)00044-8"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] J. Zheng, C. Huang, M. Chu, F.K. Soong, and W. Ye, \u201cGeneralized Segment Posterior Probability for Automatic Mandarin Pronunciation Evaluation,\u201d Proc. ICASSP, p.IV-201, 2007. 10.1109\/icassp.2007.367198","DOI":"10.1109\/ICASSP.2007.367198"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] F. Zhang, C. Huang, F.K. Soong, M. Chu, and R.H. Wang, \u201cAutomatic mispronunciation detection for Mandarin,\u201d Proc. ICASSP, pp.5077-5080, 2008. 10.1109\/icassp.2008.4518800","DOI":"10.21437\/Interspeech.2008-658"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] Y. Song and W. Liang, \u201cExperimental Study of Discriminative Adaptive Training and MLLR for Automatic Pronunciation Evaluation,\u201d Proc. Tsinghua Science & Technology, pp.189-193, 2011.","DOI":"10.1016\/S1007-0214(11)70029-3"},{"key":"14","unstructured":"[14] J. Zhang, F. Pan, B. Dong, Q. Zhao, and Y. Yan, \u201cA Novel Discriminative Method for Pronunciation Quality Assessment,\u201d Proc. IEICE, 96(5), pp.1145-1151, 2013."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] W. Hu, Y. Qian, F.K. Soong, and Y. Wang, \u201cImproved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers,\u201d Proc. Speech Communication, vol.67, pp.154-166, 2015.","DOI":"10.1016\/j.specom.2014.12.008"},{"key":"16","unstructured":"[16] K. Truong, N. Ambra, C. Cucchiarini, and H. Strik, \u201cAutomatic pronunciation error detection: an acoustic-phonetic approach,\u201d Proc. InSTIL\/ICALL Symposiumon on Computer Assisted Learning, pp.135-138, 2004."},{"key":"17","unstructured":"[17] H. Strik, K. Truong, F. De Wet, and C. Cucchiarini, \u201cComparing classifiers for pronunciation error detection,\u201d Proc. Interspeech, pp.1837-1840, 2007."},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] H. Strik, K. Truong, F. De Wet, and C. Cucchiarini, \u201cComparing different approaches for automatic pronunciation error detection,\u201d Proc. Speech Communication, vol.51, pp.845-852, 2009.","DOI":"10.1016\/j.specom.2009.05.007"},{"key":"19","unstructured":"[19] Y. Tsubota, T. Kawahara, and M. Dantsuji, \u201cRecognition and verification of English by Japanese students for computer-assisted language learning system,\u201d Proc. ICSLP, pp.1205-1208, 2002."},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] H. Meng, Y.Y. Lo, L. Wang, and W.Y. Lau, \u201cDeriving salient learners' mispronunciations from cross-language phonological comparisons,\u201d Proc. ASRU, pp.437-442, 2007. 10.1109\/asru.2007.4430152","DOI":"10.1109\/ASRU.2007.4430152"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] Y.-B. Wang and L.-S. Lee, \u201cImproved approaches of modeling and detecting error patterns with empirical analysis for computer-aided pronunciation training,\u201d Proc. ICASSP, pp.5049-5052, 2012. 10.1109\/icassp.2012.6289055","DOI":"10.1109\/ICASSP.2012.6289055"},{"key":"22","unstructured":"[22] Y.-B. Wang and L.-S. Lee, \u201cToward unsupervised discovery of pronunciation error patterns using universal phoneme posteriorgram for computer-assisted language learning,\u201d Proc. ICASSP, pp.8232-8236, 2013."},{"key":"23","unstructured":"[23] A. Lee and J. Glass, \u201cContext-dependent pronunciation error pattern discovery with limited annotation,\u201d Proc. Interspeech, pp.2877-2881, 2014."},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] A. Lee and J. Glass, \u201cMispronunciation Detection without Nonnative Training Data,\u201d Proc. Interspeech, pp.643-647, 2015.","DOI":"10.21437\/Interspeech.2015-232"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] S. Joshi, N. Deo, and P. Rao, \u201cVowel mispronunciation detection using DNN acoustic models with cross-lingual training,\u201d Proc. Interspeech, pp.697-701, 2015.","DOI":"10.21437\/Interspeech.2015-243"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] P. Badin, Y. Tarabalka, F. Flisei, and G. Baily, \u201cCan you \u2018read\u2019 tongue movements? Evaluation of the contribution of tongue display to speech understanding,\u201d Proc. Speech Communication, vol.52, pp.493-503, 2010.","DOI":"10.1016\/j.specom.2010.03.002"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] S. Fagel and K. Madany, \u201cA 3D virtual head as a tool for speech therapy for children,\u201d Proc. Interspeech, pp.2643-2646, 2008","DOI":"10.21437\/Interspeech.2008-655"},{"key":"28","unstructured":"[28] A. Rathinavelu, H. Thiagarajan, and A. Rajkumar, \u201cThree dimensional articulator model for speech acquisition by children with hearing loss,\u201d Proc. 4th Internation Conference on Universal Access in Human Computer Interaction, vol.4554, pp.786-794, 2007."},{"key":"29","unstructured":"[29] M.E. Taylor and P. Stone, \u201cTransfer learning for reinforcement learning domains: A survey,\u201d Proc. Journal of Machine Learning Research, vol.10, pp.1633-1685, 2009."},{"key":"30","unstructured":"[30] S.J. Pan and Q. Yang, \u201cA survey on transfer learning,\u201d Proc. IEEE Trans. Knowl. Data Eng., vol.22, no.10, pp.1345-1359, 2010."},{"key":"31","unstructured":"[31] Y. Bengio, \u201cDeep learning of representations for unsupervised and transfer learning,\u201d Proc. ICML Unsupervised and Transfer Learning, pp.17-36, 2012."},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] J. Lu, V. Behbood, P. Hao, H. Zuo, S. Xue, and G. Zhang, \u201cTransfer learning using computational intelligence: A survey,\u201d Proc. Knowledge-Based Systems, vol.80, pp.14-23, 2015.","DOI":"10.1016\/j.knosys.2015.01.010"},{"key":"33","unstructured":"[33] J. Zhang, Chinese man-machine voice communication infrastructure, Shanghai Science and Technology Press, 2010."},{"key":"34","unstructured":"[34] X. Pi, Japanese Summary, Shanghai Foreign Language Education Press, 1997."},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] R. Rasipuram and M. Magimai-Doss, \u201cImproving articulatory feature and phoneme recognition using multitask learning,\u201d Proc. International Conference on Artificial Neural Networks, pp.299-306, Springer Berlin Heidelberg, 2011. 10.1007\/978-3-642-21735-7_37","DOI":"10.1007\/978-3-642-21735-7_37"},{"key":"36","unstructured":"[36] T. Cohn and L. Specia, \u201cModelling Annotator Bias with Multi-task Gaussian Processes: An Application to Machine Translation Quality Estimation,\u201d Proc. ACL, pp.32-42, 2013."},{"key":"37","unstructured":"[37] W. Zhang, R. Li, T. Zeng, Q. Sun, S. Kumar, J. Ye, and S. Ji, \u201cDeep model based transfer and multi-task learning for biological image analysis,\u201d Proc. ACM SIGKDD, pp.1475-1484, 2015."},{"key":"38","doi-asserted-by":"crossref","unstructured":"[38] L. Postman and K. Stark, \u201cRole of response availability in transfer and interference,\u201d Proc. Journal of Experimental Psychology, 79.1p1, 168, 1969.","DOI":"10.1037\/h0026932"},{"key":"39","unstructured":"[39] J.D. Bransford, A.L. Brown, and R.R. Cocking, \u201cHow people learn: Brain, mind, experience, and school,\u201d Wasington, DC, National Academy Press, 1999."},{"key":"40","unstructured":"[40] C.B. Chang and A. Mishler, \u201cEvidence for language transfer leading to a perceptual advantage for non-native listeners,\u201d Proc. Journal of the Acoustical Society of America, vol.132, no.4, pp.2700-2710, 2012."},{"key":"41","unstructured":"[41] J.G. Fiscus, \u201cA post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER),\u201d Proc. IEEE Workshop on Automatic Speech Recognition and Understanding, pp.347-354, 1997. 10.1109\/asru.1997.659110"},{"key":"42","unstructured":"[42] G. Evermann and P. Woodland, \u201cPosterior probability decoding, confidence estimation, and system combination,\u201d Proc. Speech Transcription Workshop, vol.27, pp.78-81, 2000."},{"key":"43","doi-asserted-by":"crossref","unstructured":"[43] S. Gao, et al., \u201cUpdate of Progress of Sinphear: Advanced Mandarin LVCSR System At NLPR,\u201d Proc. ICSLP, pp.798-801, 2000.","DOI":"10.21437\/ICSLP.2000-655"},{"key":"44","doi-asserted-by":"crossref","unstructured":"[44] K. Itou, M. Yamamoto, K. Takeda, T. Takezawa, T. Matsuoka, T. Kobayashi, K. Shikano, and S. Itahashi, \u201cJNAS: Japanese speech corpus for large vocabulary continuous speech recognition research,\u201d Proc. Journal of the Acoustical Society of Japan, vol.20, no.3, pp.199-206.","DOI":"10.1250\/ast.20.199"},{"key":"45","unstructured":"[45] W. Cao, D. Wang, J. Zhang, and Z. Xiong, \u201cDeveloping A Chinese L2 Speech Database of Japanese Learners With Narrow-Phonetic Labels For Computer Assisted Pronunciation Training,\u201d Proc. Interspeech, pp.1922-1925, 2010."},{"key":"46","unstructured":"[46] X. Xie, \u201cA study on Japanese Learner's Acquisition process ofMandarin Balade-Palatal Initials,\u201d Proc. Jilin Teachers Institute of Engineering and Technology, vol.26, no.7, pp.23-27, 2010."},{"key":"47","unstructured":"[47] F. Li and W. Cao, \u201cComparative study on the acoustic characteristic of phoneme \/u\/ in mandarin between Chinese native speakers and Japanese learners,\u201d Proc. Chinese Master's Thesis Full-text Database, no.S1, pp.122-124, 2011."},{"key":"48","unstructured":"[48] Y. Wang and X. Shangguan, \u201cHow Japanese learners of Chinese process the aspirated and unaspirated consonants in standard Chinese,\u201d Proc. Chinese Teaching in the World, vol.3, pp.54-56, 2004."},{"key":"49","doi-asserted-by":"crossref","unstructured":"[49] H. Xu, D. Povey, L. Mangu, and J. Zhu, \u201cMinimum bayes risk decoding and system combination based on a recursion for edit distance,\u201d Computer Speech & Language, vol.25, no.4, pp.802-828, 2011. 10.1016\/j.csl.2011.03.001","DOI":"10.1016\/j.csl.2011.03.001"},{"key":"50","doi-asserted-by":"crossref","unstructured":"[50] W. Li, S.M. Siniscalchi, N.F. Chen, and C.-H. Lee, \u201cImproving non-native mispronunciation detection and enriching diagnostic feedback with DNN-based speech attribute modeling,\u201d Proc. ICASSP, pp.6135-6139, 2016. 10.1109\/icassp.2016.7472856","DOI":"10.1109\/ICASSP.2016.7472856"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E100.D\/9\/E100.D_2017EDP7019\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T12:26:37Z","timestamp":1750854397000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E100.D\/9\/E100.D_2017EDP7019\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":50,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2017]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2017edp7019","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2017]]}}}