{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T08:57:21Z","timestamp":1769504241865,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":89,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T00:00:00Z","timestamp":1620259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the state key program of the National Natural Science Foundation of China (NSFC)","award":["No.61831022"],"award-info":[{"award-number":["No.61831022"]}]},{"name":"National Key R&D Program of China","award":["No. 2020AAA0108600"],"award-info":[{"award-number":["No. 2020AAA0108600"]}]},{"name":"National Key Research and Development Project of China","award":["No.2019YFB1405700"],"award-info":[{"award-number":["No.2019YFB1405700"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,5,6]]},"DOI":"10.1145\/3411764.3445490","type":"proceedings-article","created":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T04:19:40Z","timestamp":1620447580000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["PTeacher: a Computer-Aided Personalized Pronunciation Training System with Exaggerated Audio-Visual Corrective Feedback"],"prefix":"10.1145","author":[{"given":"Yaohua","family":"Bu","sequence":"first","affiliation":[{"name":"Academy of Arts & Design Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology Northeast Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Electronic Engineering The Chinese University of Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Jia","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengqi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiyuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dachuan","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haozhe","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihan","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Li","sequence":"additional","affiliation":[{"name":"Speech X Limited, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanchun","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Computer science and Technology Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"Lu","sequence":"additional","affiliation":[{"name":"Academy of Arts & Design Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,5,7]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.08.010"},{"key":"e_1_3_2_2_2_1","unstructured":"Pierre Badin Atef\u00a0Ben Youssef G\u00e9rard Bailly Fr\u00e9d\u00e9ric Elisei and Thomas Hueber. 2010. Visual articulatory feedback for phonetic correction in second language learning. In Second Language Studies: Acquisition Learning Education and Technology. Pierre Badin Atef\u00a0Ben Youssef G\u00e9rard Bailly Fr\u00e9d\u00e9ric Elisei and Thomas Hueber. 2010. Visual articulatory feedback for phonetic correction in second language learning. In Second Language Studies: Acquisition Learning Education and Technology."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1075\/jslp.00006.bli"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.418276"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1159\/000261913"},{"key":"e_1_3_2_2_6_1","first-page":"599","article-title":"Device, method, and graphical user interface for providing audiovisual feedback","volume":"10","author":"Brown I","year":"2020","unstructured":"Matthew\u00a0 I Brown and Avi\u00a0 E Cieplinski . 2020 . Device, method, and graphical user interface for providing audiovisual feedback . US Patent 10 , 599 ,394. Matthew\u00a0I Brown and Avi\u00a0E Cieplinski. 2020. Device, method, and graphical user interface for providing audiovisual feedback. US Patent 10,599,394.","journal-title":"US Patent"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3241397"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414444"},{"key":"e_1_3_2_2_9_1","unstructured":"Eva Cervi\u00f1o-Povedano and Joan\u00a0C Mora. 2010. Investigating Catalan learners of English over-reliance on duration: Vowel cue weighting and phonological short-term memory. Achievements and perspectives in the acquisition of second language speech: New Sounds (2010) 53\u201364. Eva Cervi\u00f1o-Povedano and Joan\u00a0C Mora. 2010. Investigating Catalan learners of English over-reliance on duration: Vowel cue weighting and phonological short-term memory. Achievements and perspectives in the acquisition of second language speech: New Sounds (2010) 53\u201364."},{"key":"e_1_3_2_2_10_1","volume-title":"Subliminal cues while teaching: HCI technique for enhanced learning. Advances in Human-Computer Interaction 2011","author":"Chalfoun Pierre","year":"2011","unstructured":"Pierre Chalfoun and Claude Frasson . 2011. Subliminal cues while teaching: HCI technique for enhanced learning. Advances in Human-Computer Interaction 2011 ( 2011 ). Pierre Chalfoun and Claude Frasson. 2011. Subliminal cues while teaching: HCI technique for enhanced learning. Advances in Human-Computer Interaction 2011 (2011)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/168642.168647"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.664274"},{"key":"e_1_3_2_2_13_1","volume-title":"The role of temporal acoustic exaggeration in high variability phonetic training: A behavioral and ERP study. Frontiers in psychology 10","author":"Cheng Bing","year":"2019","unstructured":"Bing Cheng , Xiaojuan Zhang , Siying Fan , and Yang Zhang . 2019. The role of temporal acoustic exaggeration in high variability phonetic training: A behavioral and ERP study. Frontiers in psychology 10 ( 2019 ), 1178. Bing Cheng, Xiaojuan Zhang, Siying Fan, and Yang Zhang. 2019. The role of temporal acoustic exaggeration in high variability phonetic training: A behavioral and ERP study. Frontiers in psychology 10 (2019), 1178."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.5136866"},{"key":"e_1_3_2_2_15_1","volume-title":"Second language speech","author":"Colantoni Laura","unstructured":"Laura Colantoni , Jeffrey Steele , Paola Escudero , and Paola Roc\u00edo\u00a0Escudero Neyra . 2015. Second language speech . Cambridge University Press . Laura Colantoni, Jeffrey Steele, Paola Escudero, and Paola Roc\u00edo\u00a0Escudero Neyra. 2015. Second language speech. Cambridge University Press."},{"key":"e_1_3_2_2_16_1","volume-title":"Basics of qualitative research: Techniques and procedures for developing grounded theory","author":"Corbin Juliet","unstructured":"Juliet Corbin and Anselm Strauss . 2014. Basics of qualitative research: Techniques and procedures for developing grounded theory . Sage publications. Juliet Corbin and Anselm Strauss. 2014. Basics of qualitative research: Techniques and procedures for developing grounded theory. Sage publications."},{"key":"e_1_3_2_2_17_1","volume-title":"Negative language transfer when learning Spanish as a foreign language. Interling\u00fc\u00edstica16","author":"Cort\u00e9s Nuria\u00a0Calvo","year":"2005","unstructured":"Nuria\u00a0Calvo Cort\u00e9s . 2005. Negative language transfer when learning Spanish as a foreign language. Interling\u00fc\u00edstica16 ( 2005 ), 237\u2013248. Nuria\u00a0Calvo Cort\u00e9s. 2005. Negative language transfer when learning Spanish as a foreign language. Interling\u00fc\u00edstica16 (2005), 237\u2013248."},{"key":"e_1_3_2_2_18_1","first-page":"2015","article-title":"The English Effect","volume":"22","author":"British Council","year":"2013","unstructured":"British Council . 2013 . The English Effect . Retrieved March 22 (2013), 2015 . British Council. 2013. The English Effect. Retrieved March 22(2013), 2015.","journal-title":"Retrieved March"},{"key":"e_1_3_2_2_19_1","volume-title":"A dictionary of linguistics and phonetics. Vol.\u00a030","author":"Crystal David","unstructured":"David Crystal . 2011. A dictionary of linguistics and phonetics. Vol.\u00a030 . John Wiley & Sons . David Crystal. 2011. A dictionary of linguistics and phonetics. Vol.\u00a030. John Wiley & Sons."},{"key":"e_1_3_2_2_20_1","volume-title":"Second language accent and pronunciation teaching: A research-based approach. TESOL quarterly 39, 3","author":"Derwing M","year":"2005","unstructured":"Tracey\u00a0 M Derwing and Murray\u00a0 J Munro . 2005. Second language accent and pronunciation teaching: A research-based approach. TESOL quarterly 39, 3 ( 2005 ), 379\u2013397. Tracey\u00a0M Derwing and Murray\u00a0J Munro. 2005. Second language accent and pronunciation teaching: A research-based approach. TESOL quarterly 39, 3 (2005), 379\u2013397."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0346-251X(02)00012-X"},{"key":"e_1_3_2_2_22_1","volume-title":"Proceedings of the 25th annual Boston University conference on language development, Vol.\u00a01. Citeseer, 250\u2013261","author":"Escudero Paola","year":"2001","unstructured":"Paola Escudero . 2001 . The role of the input in the development of L1 and L2 sound contrasts: language-specific cue weighting for vowels . In Proceedings of the 25th annual Boston University conference on language development, Vol.\u00a01. Citeseer, 250\u2013261 . Paola Escudero. 2001. The role of the input in the development of L1 and L2 sound contrasts: language-specific cue weighting for vowels. In Proceedings of the 25th annual Boston University conference on language development, Vol.\u00a01. Citeseer, 250\u2013261."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008166717597"},{"key":"e_1_3_2_2_25_1","unstructured":"Christina Garcia Mark Kolat and Terrell\u00a0A Morgan. 2018. SELF-CORRECTION OF SECOND-LANGUAGE PRONUNCIATION VIA ONLINE REAL-TIME VISUAL FEEDBACK. In PRONUNCIATION IN SECOND LANGUAGE LEARNING AND TEACHING CONFERENCE (ISSN 2380-9566). 54. Christina Garcia Mark Kolat and Terrell\u00a0A Morgan. 2018. SELF-CORRECTION OF SECOND-LANGUAGE PRONUNCIATION VIA ONLINE REAL-TIME VISUAL FEEDBACK. In PRONUNCIATION IN SECOND LANGUAGE LEARNING AND TEACHING CONFERENCE (ISSN 2380-9566). 54."},{"key":"e_1_3_2_2_26_1","volume-title":"16th International Symposium of Laser Techniques to Fluid Mechanics","author":"Geoghegan H","year":"2012","unstructured":"Patrick\u00a0 H Geoghegan , C Spence , Wei\u00a0 H Ho , X Lu , M Jermy , P Hunter , and J Cater . 2012 . Stereoscopic PIV measurement of airflow in human speech during pronunciation of fricatives . In 16th International Symposium of Laser Techniques to Fluid Mechanics , Lisbon, Portugal, 9th-12th July. Patrick\u00a0H Geoghegan, C Spence, Wei\u00a0H Ho, X Lu, M Jermy, P Hunter, and J Cater. 2012. Stereoscopic PIV measurement of airflow in human speech during pronunciation of fricatives. In 16th International Symposium of Laser Techniques to Fluid Mechanics, Lisbon, Portugal, 9th-12th July."},{"key":"e_1_3_2_2_27_1","volume-title":"Technologies for foreign language learning: a review of technology types and their effectiveness. Computer assisted language learning 27, 1","author":"Golonka M","year":"2014","unstructured":"Ewa\u00a0 M Golonka , Anita\u00a0 R Bowles , Victor\u00a0 M Frank , Dorna\u00a0 L Richardson , and Suzanne Freynik . 2014. Technologies for foreign language learning: a review of technology types and their effectiveness. Computer assisted language learning 27, 1 ( 2014 ), 70\u2013105. Ewa\u00a0M Golonka, Anita\u00a0R Bowles, Victor\u00a0M Frank, Dorna\u00a0L Richardson, and Suzanne Freynik. 2014. Technologies for foreign language learning: a review of technology types and their effectiveness. Computer assisted language learning 27, 1 (2014), 70\u2013105."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242671.3242694"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1518774"},{"key":"e_1_3_2_2_30_1","volume-title":"On feature spreading and the representation of place of articulation. Linguistic inquiry 31, 3","author":"Halle Morris","year":"2000","unstructured":"Morris Halle , Bert Vaux , and Andrew Wolfe . 2000. On feature spreading and the representation of place of articulation. Linguistic inquiry 31, 3 ( 2000 ), 387\u2013444. Morris Halle, Bert Vaux, and Andrew Wolfe. 2000. On feature spreading and the representation of place of articulation. Linguistic inquiry 31, 3 (2000), 387\u2013444."},{"key":"e_1_3_2_2_31_1","unstructured":"CC Hsu. [n.d.]. Python-wrapper-for-world-vocoder. CC Hsu. [n.d.]. Python-wrapper-for-world-vocoder."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1177\/1046878102332009"},{"key":"e_1_3_2_2_33_1","volume-title":"Twelfth Annual Conference of the International Speech Communication Association.","author":"Iribe Yurie","year":"2011","unstructured":"Yurie Iribe , Silasak Manosavanh , Kouichi Katsurada , Ryoko Hayashi , Chunyue Zhu , and Tsuneo Nitta . 2011 . Generating animated pronunciation from speech through articulatory feature extraction . In Twelfth Annual Conference of the International Speech Communication Association. Yurie Iribe, Silasak Manosavanh, Kouichi Katsurada, Ryoko Hayashi, Chunyue Zhu, and Tsuneo Nitta. 2011. Generating animated pronunciation from speech through articulatory feature extraction. In Twelfth Annual Conference of the International Speech Communication Association."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1972.1162353"},{"key":"e_1_3_2_2_35_1","volume-title":"On the effects of L2 perception and of individual differences in L1 production on L2 pronunciation. Frontiers in psychology 5","author":"Kartushina Natalia","year":"2014","unstructured":"Natalia Kartushina and Ulrich\u00a0 H Frauenfelder . 2014. On the effects of L2 perception and of individual differences in L1 production on L2 pronunciation. Frontiers in psychology 5 ( 2014 ), 1246. Natalia Kartushina and Ulrich\u00a0H Frauenfelder. 2014. On the effects of L2 perception and of individual differences in L1 production on L2 pronunciation. Frontiers in psychology 5 (2014), 1246."},{"key":"e_1_3_2_2_36_1","volume-title":"The effect of phonetic production training with visual feedback on the perception and production of foreign speech sounds. The journal of the acoustical society of America 138, 2","author":"Kartushina Natalia","year":"2015","unstructured":"Natalia Kartushina , Alexis Hervais-Adelman , Ulrich\u00a0Hans Frauenfelder , and Narly Golestani . 2015. The effect of phonetic production training with visual feedback on the perception and production of foreign speech sounds. The journal of the acoustical society of America 138, 2 ( 2015 ), 817\u2013832. Natalia Kartushina, Alexis Hervais-Adelman, Ulrich\u00a0Hans Frauenfelder, and Narly Golestani. 2015. The effect of phonetic production training with visual feedback on the perception and production of foreign speech sounds. The journal of the acoustical society of America 138, 2 (2015), 817\u2013832."},{"key":"e_1_3_2_2_37_1","volume-title":"Eighth International Conference on Spoken Language Processing.","author":"Kawahara Tatsuya","year":"2004","unstructured":"Tatsuya Kawahara , Masatake Dantsuji , and Yasushi Tsubota . 2004 . Practical use of English pronunciation system for Japanese students in the CALL classroom . In Eighth International Conference on Spoken Language Processing. Tatsuya Kawahara, Masatake Dantsuji, and Yasushi Tsubota. 2004. Practical use of English pronunciation system for Japanese students in the CALL classroom. In Eighth International Conference on Spoken Language Processing."},{"key":"e_1_3_2_2_38_1","unstructured":"Gerald Kelly. 2006. How To Teach Pronunciation (With Cd). Pearson Education India. Gerald Kelly. 2006. How To Teach Pronunciation (With Cd). Pearson Education India."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"P Khul K Williams F Lacerda and K\u00a0Lindblom Stevens. [n.d.]. B.(1992). Linguistic Experience Alters Phonetic Perception in Infants by 6 Months of Age. Science 255([n.\u00a0d.]). P Khul K Williams F Lacerda and K\u00a0Lindblom Stevens. [n.d.]. B.(1992). Linguistic Experience Alters Phonetic Perception in Infants by 6 Months of Age. Science 255([n.\u00a0d.]).","DOI":"10.1126\/science.1736364"},{"key":"e_1_3_2_2_40_1","volume-title":"Integration of visual and auditory information in bimodal neurones in the guinea-pig superior colliculus. Experimental brain research 60, 3","author":"King AJ","year":"1985","unstructured":"AJ King and AR Palmer . 1985. Integration of visual and auditory information in bimodal neurones in the guinea-pig superior colliculus. Experimental brain research 60, 3 ( 1985 ), 492\u2013500. AJ King and AR Palmer. 1985. Integration of visual and auditory information in bimodal neurones in the guinea-pig superior colliculus. Experimental brain research 60, 3 (1985), 492\u2013500."},{"key":"e_1_3_2_2_41_1","volume-title":"Speech: articulation and perception. Vol.\u00a030. US Department of Commerce","author":"Kozhevnikov Valeri\u00a0Aleksandrovich","unstructured":"Valeri\u00a0Aleksandrovich Kozhevnikov and Liudmila\u00a0Andreevna Chistovich . 1967. Speech: articulation and perception. Vol.\u00a030. US Department of Commerce , Clearinghouse for Federal Scientific and \u00a0\u2026. Valeri\u00a0Aleksandrovich Kozhevnikov and Liudmila\u00a0Andreevna Chistovich. 1967. Speech: articulation and perception. Vol.\u00a030. US Department of Commerce, Clearinghouse for Federal Scientific and\u00a0\u2026."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/37401.37407"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0272263115000194"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.system.2019.102185"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682654"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CogInfoCom.2013.6719170"},{"key":"e_1_3_2_2_47_1","volume-title":"Rating Algorithm for Pronunciation of English Based on Audio Feature Pattern Matching. In MATEC Web of Conferences, Vol.\u00a022","author":"Li Kun","year":"2015","unstructured":"Kun Li , Jing Li , Yufang Song , and Hewei Fu . 2015 . Rating Algorithm for Pronunciation of English Based on Audio Feature Pattern Matching. In MATEC Web of Conferences, Vol.\u00a022 . EDP Sciences, 01032. Kun Li, Jing Li, Yufang Song, and Hewei Fu. 2015. Rating Algorithm for Pronunciation of English Based on Audio Feature Pattern Matching. In MATEC Web of Conferences, Vol.\u00a022. EDP Sciences, 01032."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","unstructured":"Kun Li Xiaojun Qian Shiyin Kang Pengfei Liu and Helen Meng. 2015. Integrating acoustic and state-transition models for free phone recognition in L2 English speech using multi-distribution deep neural networks.. In SLaTE. 119\u2013124. Kun Li Xiaojun Qian Shiyin Kang Pengfei Liu and Helen Meng. 2015. Integrating acoustic and state-transition models for free phone recognition in L2 English speech using multi-distribution deep neural networks.. In SLaTE. 119\u2013124.","DOI":"10.21437\/SLaTE.2015-21"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2621675"},{"key":"e_1_3_2_2_50_1","volume-title":"The discrimination of speech sounds within and across phoneme boundaries.Journal of experimental psychology 54, 5","author":"Liberman M","year":"1957","unstructured":"Alvin\u00a0 M Liberman , Katherine\u00a0Safford Harris , Howard\u00a0 S Hoffman , and Belver\u00a0 C Griffith . 1957. The discrimination of speech sounds within and across phoneme boundaries.Journal of experimental psychology 54, 5 ( 1957 ), 358. Alvin\u00a0M Liberman, Katherine\u00a0Safford Harris, Howard\u00a0S Hoffman, and Belver\u00a0C Griffith. 1957. The discrimination of speech sounds within and across phoneme boundaries.Journal of experimental psychology 54, 5 (1957), 358."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1080\/09658410008667146"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300602"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2012.6423507"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-011-9124-2"},{"key":"e_1_3_2_2_55_1","volume-title":"Eleventh Annual Conference of the International Speech Communication Association.","author":"Lu Jingli","year":"2010","unstructured":"Jingli Lu , Ruili Wang , Liyanage C\u00a0De Silva , Yang Gao , and Jia Liu . 2010 . CASTLE: a computer-assisted stress teaching and learning environment for learners of English as a second language . In Eleventh Annual Conference of the International Speech Communication Association. Jingli Lu, Ruili Wang, Liyanage C\u00a0De Silva, Yang Gao, and Jia Liu. 2010. CASTLE: a computer-assisted stress teaching and learning environment for learners of English as a second language. In Eleventh Annual Conference of the International Speech Communication Association."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"crossref","unstructured":"Michael McAuliffe Michaela Socolof Sarah Mihuc Michael Wagner and Morgan Sonderegger. 2017. Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi.. In Interspeech Vol.\u00a02017. 498\u2013502. Michael McAuliffe Michaela Socolof Sarah Mihuc Michael Wagner and Morgan Sonderegger. 2017. Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi.. In Interspeech Vol.\u00a02017. 498\u2013502.","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"e_1_3_2_2_57_1","unstructured":"Fanbo Meng Helen Meng Zhiyong Wu and Lianhong Cai. 2010. Synthesizing expressive speech to convey focus using a perturbation model for computer-aided pronunciation training. In Second Language Studies: Acquisition Learning Education and Technology. Fanbo Meng Helen Meng Zhiyong Wu and Lianhong Cai. 2010. Synthesizing expressive speech to convey focus using a perturbation model for computer-aided pronunciation training. In Second Language Studies: Acquisition Learning Education and Technology."},{"key":"e_1_3_2_2_58_1","volume-title":"Synthesizing English emphatic speech for multimodal corrective feedback in computer-aided pronunciation training. Multimedia tools and applications 73, 1","author":"Meng Fanbo","year":"2014","unstructured":"Fanbo Meng , Zhiyong Wu , Jia Jia , Helen Meng , and Lianhong Cai . 2014. Synthesizing English emphatic speech for multimodal corrective feedback in computer-aided pronunciation training. Multimedia tools and applications 73, 1 ( 2014 ), 463\u2013489. Fanbo Meng, Zhiyong Wu, Jia Jia, Helen Meng, and Lianhong Cai. 2014. Synthesizing English emphatic speech for multimodal corrective feedback in computer-aided pronunciation training. Multimedia tools and applications 73, 1 (2014), 463\u2013489."},{"key":"e_1_3_2_2_59_1","volume-title":"Thirteenth Annual Conference of the International Speech Communication Association.","author":"Meng Fanbo","year":"2012","unstructured":"Fanbo Meng , Zhiyong Wu , Helen Meng , Jia Jia , and Lianhong Cai . 2012 . Hierarchical English emphatic speech synthesis based on HMM with limited training data . In Thirteenth Annual Conference of the International Speech Communication Association. Fanbo Meng, Zhiyong Wu, Helen Meng, Jia Jia, and Lianhong Cai. 2012. Hierarchical English emphatic speech synthesis based on HMM with limited training data. In Thirteenth Annual Conference of the International Speech Communication Association."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430152"},{"key":"e_1_3_2_2_61_1","volume-title":"Major American Higher Education Issues and Challenges in the","author":"Miller I","year":"1990","unstructured":"Richard\u00a0 I Miller . 1990. Major American Higher Education Issues and Challenges in the 1990 s. Higher Education Policy Series 9.ERIC. Richard\u00a0I Miller. 1990. Major American Higher Education Issues and Challenges in the 1990s. Higher Education Policy Series 9.ERIC."},{"key":"e_1_3_2_2_62_1","unstructured":"Joan\u00a0C Mora and Isabelle Darcy. 2017. The relationship between cognitive control and pronunciation in a second language. Second language pronunciation assessment(2017) 95. Joan\u00a0C Mora and Isabelle Darcy. 2017. The relationship between cognitive control and pronunciation in a second language. Second language pronunciation assessment(2017) 95."},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1006\/jpho.1999.0101"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"crossref","unstructured":"Ambra Neri Catia Cucchiarini and Helmer Strik. 2006. ASR corrective feedback on pronunciation: Does it really work?(2006). Ambra Neri Catia Cucchiarini and Helmer Strik. 2006. ASR corrective feedback on pronunciation: Does it really work?(2006).","DOI":"10.21437\/Interspeech.2006-543"},{"key":"e_1_3_2_2_65_1","volume-title":"The pedagogy-technology interface in computer assisted pronunciation training. Computer assisted language learning 15, 5","author":"Neri Ambra","year":"2002","unstructured":"Ambra Neri , Catia Cucchiarini , Helmer Strik , and Lou Boves . 2002. The pedagogy-technology interface in computer assisted pronunciation training. Computer assisted language learning 15, 5 ( 2002 ), 441\u2013467. Ambra Neri, Catia Cucchiarini, Helmer Strik, and Lou Boves. 2002. The pedagogy-technology interface in computer assisted pronunciation training. Computer assisted language learning 15, 5 (2002), 441\u2013467."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1080\/09588220802447651"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178909"},{"key":"e_1_3_2_2_68_1","volume-title":"Introduction to English Phonetics","author":"Ogden Richard","unstructured":"Richard Ogden . 2017. Introduction to English Phonetics . Edinburgh university press . Richard Ogden. 2017. Introduction to English Phonetics. Edinburgh university press."},{"key":"e_1_3_2_2_69_1","volume-title":"Proceedings of the 12th European Conference on Research Methods for Business and Management Studies. 304\u2013314","author":"Oliveira Mirian","year":"2013","unstructured":"Mirian Oliveira , Claudia Bitencourt , Eduardo Teixeira , and Ana\u00a0Clarissa Santos . 2013 . Thematic content analysis: Is there a difference between the support provided by the MAXQDA\u00ae and NVivo\u00ae software packages . In Proceedings of the 12th European Conference on Research Methods for Business and Management Studies. 304\u2013314 . Mirian Oliveira, Claudia Bitencourt, Eduardo Teixeira, and Ana\u00a0Clarissa Santos. 2013. Thematic content analysis: Is there a difference between the support provided by the MAXQDA\u00ae and NVivo\u00ae software packages. In Proceedings of the 12th European Conference on Research Methods for Business and Management Studies. 304\u2013314."},{"key":"e_1_3_2_2_70_1","volume-title":"Proceedings of the International Congress of Phonetics Sciences. 117\u2013120","author":"Ortega Marta","year":"1999","unstructured":"Marta Ortega and Valerie Hazan . 1999 . Enhancing acoustic cues to aid L2 speech perception . In Proceedings of the International Congress of Phonetics Sciences. 117\u2013120 . Marta Ortega and Valerie Hazan. 1999. Enhancing acoustic cues to aid L2 speech perception. In Proceedings of the International Congress of Phonetics Sciences. 117\u2013120."},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1076\/call.12.5.427.5693"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"crossref","unstructured":"Linda Polka and Janet\u00a0F Werker. 1994. Developmental changes in perception of nonnative vowel contrasts.Journal of Experimental Psychology: Human perception and performance 20 2(1994) 421. Linda Polka and Janet\u00a0F Werker. 1994. Developmental changes in perception of nonnative vowel contrasts.Journal of Experimental Psychology: Human perception and performance 20 2(1994) 421.","DOI":"10.1037\/0096-1523.20.2.421"},{"key":"e_1_3_2_2_74_1","volume-title":"Fastspeech: Fast, robust and controllable text to speech. In Advances in Neural Information Processing Systems. 3171\u20133180.","author":"Ren Yi","year":"2019","unstructured":"Yi Ren , Yangjun Ruan , Xu Tan , Tao Qin , Sheng Zhao , Zhou Zhao , and Tie-Yan Liu . 2019 . Fastspeech: Fast, robust and controllable text to speech. In Advances in Neural Information Processing Systems. 3171\u20133180. Yi Ren, Yangjun Ruan, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2019. Fastspeech: Fast, robust and controllable text to speech. In Advances in Neural Information Processing Systems. 3171\u20133180."},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157814"},{"key":"e_1_3_2_2_76_1","volume-title":"Beyond Fossilization: A Course in Strategies and Techniques in Pronunciation for Advanced Adult Learners.TESL Canada Journal","author":"Ricard Ellen","year":"1986","unstructured":"Ellen Ricard . 1986 . Beyond Fossilization: A Course in Strategies and Techniques in Pronunciation for Advanced Adult Learners.TESL Canada Journal (1986), 243\u2013253. Ellen Ricard. 1986. Beyond Fossilization: A Course in Strategies and Techniques in Pronunciation for Advanced Adult Learners.TESL Canada Journal (1986), 243\u2013253."},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173930"},{"key":"e_1_3_2_2_78_1","volume-title":"English phonology and pronunciation teaching","author":"Rogerson-Revell Pamela","unstructured":"Pamela Rogerson-Revell . 2011. English phonology and pronunciation teaching . Bloomsbury Publishing . Pamela Rogerson-Revell. 2011. English phonology and pronunciation teaching. Bloomsbury Publishing."},{"key":"e_1_3_2_2_79_1","unstructured":"Winifred Strange. 1995. Speech perception and linguistic experience: Theoretical and methodological issues. Winifred Strange. 1995. Speech perception and linguistic experience: Theoretical and methodological issues."},{"key":"e_1_3_2_2_80_1","volume-title":"Speech perception in second language learners: The re-education of selective perception. Phonology and second language acquisition 36","author":"Strange Winifred","year":"2008","unstructured":"Winifred Strange , Valerie\u00a0 L Shafer , 2008. Speech perception in second language learners: The re-education of selective perception. Phonology and second language acquisition 36 ( 2008 ), 153\u2013192. Winifred Strange, Valerie\u00a0L Shafer, 2008. Speech perception in second language learners: The re-education of selective perception. Phonology and second language acquisition 36 (2008), 153\u2013192."},{"key":"e_1_3_2_2_81_1","unstructured":"Frank Thomas Ollie Johnston and Frank Thomas. 1995. The illusion of life: Disney animation. Hyperion New York. Frank Thomas Ollie Johnston and Frank Thomas. 1995. The illusion of life: Disney animation. Hyperion New York."},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"crossref","unstructured":"Ingo\u00a0R Titze and Daniel\u00a0W Martin. 1998. Principles of voice production. Ingo\u00a0R Titze and Daniel\u00a0W Martin. 1998. Principles of voice production.","DOI":"10.1121\/1.424266"},{"key":"e_1_3_2_2_83_1","unstructured":"Nikolai\u00a0Sergeevich Trubetzkoy. 1969. Principles of phonology.(1969). Nikolai\u00a0Sergeevich Trubetzkoy. 1969. Principles of phonology.(1969)."},{"key":"e_1_3_2_2_84_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10639-015-9389-1"},{"key":"e_1_3_2_2_85_1","doi-asserted-by":"publisher","DOI":"10.1044\/jslhr.4305.1229"},{"key":"e_1_3_2_2_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2010.5684832"},{"key":"e_1_3_2_2_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2011.6085985"},{"key":"e_1_3_2_2_88_1","volume-title":"Auditory perception in vestibular neurectomy subjects. Hearing research 142, 1-2","author":"Zeng Fan-Gang","year":"2000","unstructured":"Fan-Gang Zeng , Kristina\u00a0 M Martino , Fred\u00a0 H Linthicum , and Sigfrid\u00a0 D Soli . 2000. Auditory perception in vestibular neurectomy subjects. Hearing research 142, 1-2 ( 2000 ), 102\u2013112. Fan-Gang Zeng, Kristina\u00a0M Martino, Fred\u00a0H Linthicum, and Sigfrid\u00a0D Soli. 2000. Auditory perception in vestibular neurectomy subjects. Hearing research 142, 1-2 (2000), 102\u2013112."},{"key":"e_1_3_2_2_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639267"},{"key":"e_1_3_2_2_90_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"e_1_3_2_2_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"}],"event":{"name":"CHI '21: CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI '21","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3411764.3445490","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3411764.3445490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:48Z","timestamp":1750195728000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3411764.3445490"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,6]]},"references-count":89,"alternative-id":["10.1145\/3411764.3445490","10.1145\/3411764"],"URL":"https:\/\/doi.org\/10.1145\/3411764.3445490","relation":{},"subject":[],"published":{"date-parts":[[2021,5,6]]},"assertion":[{"value":"2021-05-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}