{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:38:11Z","timestamp":1740148691968,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T00:00:00Z","timestamp":1585008000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T00:00:00Z","timestamp":1585008000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Advanced Innovation Center for Language Resources and Intelligence","award":["KYR17005"],"award-info":[{"award-number":["KYR17005"]}]},{"name":"The Fundamental Research Funds for the Central Universities","award":["16ZDJ03"],"award-info":[{"award-number":["16ZDJ03"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1007\/s11265-019-01485-2","type":"journal-article","created":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T18:02:54Z","timestamp":1585072974000},"page":"793-803","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Improving Pronunciation Erroneous Tendency Detection with Multi-Model Soft Targets"],"prefix":"10.1007","volume":"92","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6970-4247","authenticated-orcid":false,"given":"Ju","family":"Lin","sequence":"first","affiliation":[]},{"given":"Yingming","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Linxuan","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Yanlu","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Jinsong","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,3,24]]},"reference":[{"key":"1485_CR1","unstructured":"Witt, S.M. (2012). Automatic error detection in pronunciation training: where we are and where we need to go. Proc IS ADEPT, vol. 6, pp. 1\u20138."},{"issue":"2-3","key":"1485_CR2","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/S0167-6393(99)00044-8","volume":"30","author":"SM Witt","year":"2000","unstructured":"Witt, S.M., & Young, S.J. (2000). Phone-level pronunciation scoring and assessment for interactive language learning. Speech communication, 30(2-3), 95\u2013108.","journal-title":"Speech communication"},{"key":"1485_CR3","unstructured":"Zhang, F., Huang, C., Soong, F.K., Chu, M., Wang, R. (2008). Automatic mispronunciation detection for mandarin. In ICASSP 2008. IEEE international conference on acoustics, speech and signal processing, 2008 (pp. 5077\u20135080): IEEE."},{"key":"1485_CR4","unstructured":"Wang, Y.-B., & Lee, L.-S. (2012). Improved approaches of modeling and detecting error patterns with empirical analysis for computer-aided pronunciation training. In 2012 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5049\u20135052): IEEE."},{"key":"1485_CR5","doi-asserted-by":"crossref","unstructured":"Lo, W. -K., Zhang, S., Meng, H. (2010). Automatic derivation of phonological rules for mispronunciation detection in a computer-assisted pronunciation training system. In Eleventh annual conference of the international speech communication association.","DOI":"10.21437\/Interspeech.2010-280"},{"key":"1485_CR6","unstructured":"Truong, K., Neri, A., Cucchiarini, C., Strik, H. (2004). Automatic pronunciation error detection: an acoustic-phonetic approach. In STIL\/ICALL symposium 2004."},{"key":"1485_CR7","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1016\/j.specom.2014.12.008","volume":"67","author":"W Hu","year":"2015","unstructured":"Hu, W., Qian, Y., Soong, F.K., Wang, Y. (2015). Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers. Speech Communication, 67, 154\u2013166.","journal-title":"Speech Communication"},{"key":"1485_CR8","doi-asserted-by":"crossref","unstructured":"Lin, J., Xie, Y., Zhang, J. (2016). Automatic pronunciation evaluation of non-native mandarin tone by using multi-level confidence measures. In Interspeech (pp. 2666\u20132670).","DOI":"10.21437\/Interspeech.2016-1162"},{"key":"1485_CR9","doi-asserted-by":"publisher","first-page":"2759","DOI":"10.21437\/Interspeech.2017-464","volume":"2017","author":"W Li","year":"2017","unstructured":"Li, W., Chen, N.F., Siniscalchi, S.M., Lee, C.-H. (2017). Improving mispronunciation detection for non-native learners with multisource information and lstm-based deep models, Proc. Interspeech, 2017, 2759\u20132763.","journal-title":"Interspeech"},{"key":"1485_CR10","doi-asserted-by":"crossref","unstructured":"Yoon, S.-Y., Hasegawa-Johnson, M., Sproat, R. (2010). Landmark-based automated pronunciation error detection. In Eleventh annual conference of the international speech communication association.","DOI":"10.21437\/Interspeech.2010-236"},{"key":"1485_CR11","doi-asserted-by":"crossref","unstructured":"Cao, W., Wang, D., Zhang, J., Xiong, Z. (2010). Developing a Chinese l2 speech database of japanese learners with narrow-phonetic labels for computer assisted pronunciation training. In Eleventh annual conference of the international speech communication association.","DOI":"10.21437\/Interspeech.2010-553"},{"key":"1485_CR12","doi-asserted-by":"crossref","unstructured":"Gao, Y., Xie, Y., Cao, W., Zhang, J. (2015). A study on robust detection of pronunciation erroneous tendency based on deep neural network. In Sixteenth annual conference of the international speech communication association.","DOI":"10.21437\/Interspeech.2015-242"},{"key":"1485_CR13","unstructured":"Gao, Y., Xie, Y., Lin, J., Zhang, J. (2016). Dnn based detection of pronunciation erroneous tendency in data sparse condition. In Signal and information processing association annual summit and conference (APSIPA), 2016 Asia-Pacific (pp. 1\u20135): IEEE."},{"key":"1485_CR14","doi-asserted-by":"crossref","unstructured":"Duan, R., Zhang, J., Cao, W., Xie, Y. (2014). A preliminary study on asr-based detection of Chinese mispronunciation by japanese learners. In Fifteenth annual conference of the international speech communication association.","DOI":"10.21437\/Interspeech.2014-360"},{"key":"1485_CR15","unstructured":"Qu, L., Xie, Y., Zhang, J. (2016). Senone log-likelihood ratios based articulatory features in pronunciation erroneous tendency detecting. In 2016 10th international symposium on Chinese spoken language processing (ISCSLP) (pp. 1\u20135): IEEE."},{"key":"1485_CR16","doi-asserted-by":"crossref","unstructured":"Wong, J.H., & Gales, M.J. (2016). Sequence student-teacher training of deep neural networks.","DOI":"10.21437\/Interspeech.2016-911"},{"key":"1485_CR17","unstructured":"Tang, Z., Wang, D., Zhang, Z. (2016). Recurrent neural network training with dark knowledge transfer. In 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5900\u20135904): IEEE."},{"key":"1485_CR18","unstructured":"Fiscus, J.G. (1997). A post-processing system to yield reduced word error rates: recognizer output voting error reduction (rover). In Proceedings., 1997 IEEE workshop on automatic speech recognition and understanding, 1997 (pp. 347\u2013354): IEEE."},{"key":"1485_CR19","unstructured":"Evermann, G., & Woodland, P. (2000). Posterior probability decoding, confidence estimation and system combination. In Proceedings Speech Transcription Workshop, vol. 27. Baltimore (pp. 78\u201381)."},{"issue":"1","key":"1485_CR20","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R. (1997). Multitask learning. Machine Learning, 28(1), 41\u201375.","journal-title":"Machine Learning"},{"key":"1485_CR21","unstructured":"Xie, X. (2010). A study on japanese learner\u2019s acquisition process of mandarin balade-palatal initials. Journal of Jilin Teachers Institute of Engineering and Technology."},{"key":"1485_CR22","unstructured":"Li, F., & Cao, W. (2011). Comparative study on the acoustic characteristic of phoneme\/u\/in mandarin between Chinese native speakers and japanese learners. Chinese Master\u2019s Thesis Full-text Database, no. S1."},{"key":"1485_CR23","doi-asserted-by":"crossref","unstructured":"Gibson, M., & Hain, T. (2006). Hypothesis spaces for minimum bayes risk training in large vocabulary speech recognition. In Ninth international conference on spoken language processing.","DOI":"10.21437\/Interspeech.2006-603"},{"key":"1485_CR24","unstructured":"Povey, D., & Kingsbury, B. (2007). Evaluation of proposed modifications to mpe for large scale discriminative training. In ICASSP 2007. IEEE international conference on acoustics, speech and signal processing, 2007, (Vol. 4 pp. IV\u2013321): IEEE."},{"issue":"4","key":"1485_CR25","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1016\/j.csl.2011.03.001","volume":"25","author":"H Xu","year":"2011","unstructured":"Xu, H., Povey, D., Mangu, L., Zhu, J. (2011). Minimum bayes risk decoding and system combination based on a recursion for edit distance. Computer Speech & Language, 25(4), 802\u2013828.","journal-title":"Computer Speech & Language"},{"key":"1485_CR26","unstructured":"Hinton, G., Vinyals, O., Dean, J. (2015). Distilling the knowledge in a neural network, arXiv preprint arXiv:http:\/\/arXiv.org\/abs\/1503.02531."},{"issue":"2","key":"1485_CR27","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1109\/72.557698","volume":"8","author":"H Bersini","year":"1997","unstructured":"Bersini, H., & Gorrini, V. (1997). A simplification of the backpropagation-through-time algorithm for optimal neurocontrol. IEEE Transactions on Neural Networks, 8(2), 437\u2013441.","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"6088","key":"1485_CR28","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533.","journal-title":"Nature"},{"key":"1485_CR29","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., et al. (2011). The kaldi speech recognition toolkit. In IEEE 2011 workshop on automatic speech recognition and understanding, no. EPFL-CONF-192584. IEEE Signal Processing Society."},{"key":"1485_CR30","doi-asserted-by":"crossref","unstructured":"Metze, F. (2005). Articulatory features for conversational speech recognition.","DOI":"10.21437\/Interspeech.2006-214"},{"issue":"9","key":"1485_CR31","doi-asserted-by":"publisher","first-page":"2174","DOI":"10.1587\/transinf.2017EDP7019","volume":"100","author":"R Duan","year":"2017","unstructured":"Duan, R., Kawahara, T., Dantsuji, M., Zhang, J. (2017). Articulatory modeling for pronunciation error detection without non-native training data based on dnn transfer learning. IEICE Transactions on Information and Systems, 100(9), 2174\u20132182.","journal-title":"IEICE Transactions on Information and Systems"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-019-01485-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-019-01485-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-019-01485-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T17:38:24Z","timestamp":1666201104000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-019-01485-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,24]]},"references-count":31,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2020,8]]}},"alternative-id":["1485"],"URL":"https:\/\/doi.org\/10.1007\/s11265-019-01485-2","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"type":"print","value":"1939-8018"},{"type":"electronic","value":"1939-8115"}],"subject":[],"published":{"date-parts":[[2020,3,24]]},"assertion":[{"value":"14 February 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}