{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T17:13:21Z","timestamp":1740158001838,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2020,6,11]],"date-time":"2020-06-11T00:00:00Z","timestamp":1591833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,6,11]],"date-time":"2020-06-11T00:00:00Z","timestamp":1591833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1007\/s12652-020-02175-9","type":"journal-article","created":{"date-parts":[[2020,6,11]],"date-time":"2020-06-11T15:04:15Z","timestamp":1591887855000},"page":"5055-5066","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Vowel priority lip matching scheme and similarity evaluation model based on humanoid robot Ren-Xin"],"prefix":"10.1007","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0685-1124","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"first","affiliation":[]},{"given":"Xin","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Shun","family":"Nishide","sequence":"additional","affiliation":[]},{"given":"Fuji","family":"Ren","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,6,11]]},"reference":[{"key":"2175_CR1","unstructured":"Binyong Y, Felley M (1990) Chinese romanization: pronunciation & orthography. Peking"},{"key":"2175_CR2","first-page":"223","volume":"243657","author":"T Cootes","year":"2000","unstructured":"Cootes T, Baldock ER, Graham J (2000) An introduction to active shape models. Image Process Anal 243657:223\u2013248","journal-title":"Image Process Anal"},{"issue":"6","key":"2175_CR3","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1109\/34.927467","volume":"23","author":"T Cootes","year":"2001","unstructured":"Cootes T, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans Pattern Anal Mach Intell 23(6):681\u2013685. https:\/\/doi.org\/10.1109\/34.927467","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2175_CR4","doi-asserted-by":"crossref","unstructured":"Dai K, Zhang Y, Wang D et al (2020) High-performance long-term tracking with meta-updater. arXiv preprint arXiv:2004.00305","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"2175_CR5","first-page":"2","volume":"4","author":"X Fan","year":"2017","unstructured":"Fan X, Yang X (2017) A speech-driven lip synchronization method. J Donghua Univ (Nat Sci) 4:2 (in Chinese)","journal-title":"J Donghua Univ (Nat Sci)"},{"key":"2175_CR6","doi-asserted-by":"publisher","unstructured":"Fu K, Sun L, Kang X et al (2019) Text detection for natural scene based on mobileNet V2 and U-Net. In: 2019 IEEE international conference on mechatronics and automation (ICMA), pp 1560\u20131564.  https:\/\/doi.org\/10.1109\/ICMA.2019.8816384","DOI":"10.1109\/ICMA.2019.8816384"},{"key":"2175_CR7","doi-asserted-by":"publisher","unstructured":"Hara F, Endou K, Shirata S (1997) Lip-Configuration Control Of A Mouth Robot For Japanese Vowels. In: Proceedings 6th IEEE International workshop on robot and human communication, pp 412\u2013418. https:\/\/doi.org\/10.1109\/ROMAN.1997.647022","DOI":"10.1109\/ROMAN.1997.647022"},{"issue":"4","key":"2175_CR8","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1109\/TCDS.2017.2787196","volume":"10","author":"DC Herath","year":"2017","unstructured":"Herath DC, Jochum E, Vlachos E (2017) An experimental study of embodied interaction and human perception of social presence for interactive robots in public settings. IEEE Trans Cogn Dev Syst 10(4):1096\u20131105. https:\/\/doi.org\/10.1109\/TCDS.2017.2787196","journal-title":"IEEE Trans Cogn Dev Syst"},{"issue":"2","key":"2175_CR9","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1109\/TCDS.2017.2714170","volume":"10","author":"J Hwang","year":"2017","unstructured":"Hwang J, Tani J (2017) Seamless integration and coordination of cognitive skills in humanoid robots: a deep learning approach. IEEE Trans Cogn Dev Syst 10(2):345\u2013358. https:\/\/doi.org\/10.1109\/TCDS.2017.2714170","journal-title":"IEEE Trans Cogn Dev Syst"},{"key":"2175_CR10","doi-asserted-by":"publisher","unstructured":"Hyung HJ, Ahn BK, Choi D et al (2016) Evaluation of a Korean Lip-sync system for an android robot. In: 2016 13th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), pp 78\u201382. https:\/\/doi.org\/10.1109\/URAI.2016.7734025","DOI":"10.1109\/URAI.2016.7734025"},{"issue":"4","key":"2175_CR11","doi-asserted-by":"publisher","first-page":"3757","DOI":"10.1109\/LRA.2018.2856281","volume":"3","author":"CT Ishi","year":"2018","unstructured":"Ishi CT, Machiyashiki D, Mikata R et al (2018) A speech-driven hand gesture generation method and evaluation in android robots. IEEE Robot Autom Lett 3(4):3757\u20133764. https:\/\/doi.org\/10.1109\/LRA.2018.2856281","journal-title":"IEEE Robot Autom Lett"},{"issue":"4","key":"2175_CR12","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1159\/000261726","volume":"41","author":"PA Keating","year":"1984","unstructured":"Keating PA, Huffman MK (1984) Vowel variation in Japanese. Phonetica 41(4):191\u2013207. https:\/\/doi.org\/10.1159\/000261726","journal-title":"Phonetica"},{"key":"2175_CR13","first-page":"97","volume":"13","author":"TH Kim","year":"2008","unstructured":"Kim TH (2008) A study on Korean lip-sync for animation characters-based on lip-sync technique in english-speaking animations. Cartoon Animat Stud 13:97\u2013114 (in Korean)","journal-title":"Cartoon Animat Stud"},{"issue":"3","key":"2175_CR14","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/s10514-015-9479-3","volume":"40","author":"S Kuindersma","year":"2016","unstructured":"Kuindersma S, Deits R, Fallon M et al (2016) Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robot. Auton Robots 40(3):429\u2013455. https:\/\/doi.org\/10.1007\/s10514-015-9479-3","journal-title":"Auton Robots"},{"key":"2175_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-018-1025-7","author":"X Li","year":"2018","unstructured":"Li X, Wang T (2018) A long time tracking with BIN-NST and DRN. J Ambient Intell Human Comput. https:\/\/doi.org\/10.1007\/s12652-018-1025-7","journal-title":"J Ambient Intell Human Comput"},{"key":"2175_CR16","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.patcog.2017.11.007","volume":"76","author":"P Li","year":"2018","unstructured":"Li P, Wang D, Wang L et al (2018) Deep visual tracking: review and experimental comparison. Pattern Recogn 76:323\u2013338. https:\/\/doi.org\/10.1016\/j.patcog.2017.11.007","journal-title":"Pattern Recogn"},{"key":"2175_CR17","doi-asserted-by":"publisher","unstructured":"Liu Z, Ren F, Kang X (2019) Research on the effect of different speech segment lengths on speech emotion recognition based on LSTM. In: Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, pp 491\u2013499. https:\/\/doi.org\/10.18178\/wcse.2019.06.073","DOI":"10.18178\/wcse.2019.06.073"},{"key":"2175_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-019-01575-w","author":"T Long","year":"2019","unstructured":"Long T (2019) Research on application of athlete gesture tracking algorithms based on deep learning. J Ambient Intell Human Comput. https:\/\/doi.org\/10.1007\/s12652-019-01575-w","journal-title":"J Ambient Intell Human Comput"},{"issue":"2","key":"2175_CR19","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1007\/s11036-017-0932-8","volume":"23","author":"H Lu","year":"2018","unstructured":"Lu H, Li Y, Chen M et al (2018) Brain intelligence: go beyond artificial intelligence. Mob Netw Appl 23(2):368\u2013375. https:\/\/doi.org\/10.1007\/s11036-017-0932-8","journal-title":"Mob Netw Appl"},{"key":"2175_CR20","doi-asserted-by":"publisher","unstructured":"Luo RC, Chang SR, Huang CC et al (2011) Human robot interactions using speech synthesis and recognition with lip synchronization. In: 2011 IECON 2011\u201337th Annual Conference of the IEEE Industrial Electronics Society, pp 171\u2013176. https:\/\/doi.org\/10.1109\/IECON.2011.6119307","DOI":"10.1109\/IECON.2011.6119307"},{"key":"2175_CR21","doi-asserted-by":"publisher","unstructured":"Miyazaki T, Nakashima T (2015) Analysis of mouth shape deformation rate for generation of Japanese utterance images automatically. In: Software engineering research, management and applications, pp 75\u201386. https:\/\/doi.org\/10.1007\/978-3-319-11265-7_6","DOI":"10.1007\/978-3-319-11265-7_6"},{"issue":"4","key":"2175_CR22","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1109\/49.81953","volume":"9","author":"S Morishima","year":"1991","unstructured":"Morishima S, Harashima H (1991) A media conversion from speech to facial image for intelligent man-machine interface. IEEE J Sel Areas Commun 9(4):594\u2013600. https:\/\/doi.org\/10.1109\/49.81953","journal-title":"IEEE J Sel Areas Commun"},{"key":"2175_CR23","doi-asserted-by":"publisher","unstructured":"Nishikawa K, Takanobu H, Mochida T et al (2004) Speech production of an advanced talking robot based on human acoustic theory. In: 2004 IEEE International Conference on Robotics and Automation(ICRA), pp 3213\u20133219. https:\/\/doi.org\/10.1109\/ROBOT.2004.1308749","DOI":"10.1109\/ROBOT.2004.1308749"},{"key":"2175_CR24","doi-asserted-by":"publisher","unstructured":"Oh KG, Jung C Y, Lee Y G et al (2010) Real-time lip synchronization between text-to-speech (TTS) system and robot mouth. In: 19th International symposium in robot and human interactive communication, pp 620\u2013625. https:\/\/doi.org\/10.1109\/ROMAN.2010.5598656","DOI":"10.1109\/ROMAN.2010.5598656"},{"key":"2175_CR25","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.entcs.2008.12.065","volume":"225","author":"F Ren","year":"2009","unstructured":"Ren F (2009) Affective information processing and recognizing human emotion. Electron Notes Theor Comput Sci 225:39\u201350. https:\/\/doi.org\/10.1016\/j.entcs.2008.12.065","journal-title":"Electron Notes Theor Comput Sci"},{"issue":"01","key":"2175_CR26","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1142\/S0219622019300052","volume":"19","author":"F Ren","year":"2020","unstructured":"Ren F, Bao Y (2020) A review on human-computer interaction and intelligent robots. Int J Inf Technol Decis Mak 19(01):5\u201347. https:\/\/doi.org\/10.1142\/S0219622019300052","journal-title":"Int J Inf Technol Decis Mak"},{"issue":"6","key":"2175_CR27","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1109\/THMS.2016.2599495","volume":"46","author":"F Ren","year":"2016","unstructured":"Ren F, Huang Z (2016) Automatic facial expression learning method based on humanoid robot XIN-REN. IEEE Trans Hum Mach Syst 46(6):810\u2013821. https:\/\/doi.org\/10.1109\/THMS.2016.2599495","journal-title":"IEEE Trans Hum Mach Syst"},{"issue":"5","key":"2175_CR28","doi-asserted-by":"publisher","first-page":"1384","DOI":"10.1109\/JBHI.2015.2459683","volume":"20","author":"F Ren","year":"2015","unstructured":"Ren F, Kang X, Quan C (2015) Examining accumulated emotional traits in suicide blogs with an emotion topic model. IEEE J Biomed Health Inform 20(5):1384\u20131396. https:\/\/doi.org\/10.1109\/JBHI.2015.2459683","journal-title":"IEEE J Biomed Health Inform"},{"issue":"2","key":"2175_CR29","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1109\/TAFFC.2015.2457915","volume":"7","author":"F Ren","year":"2015","unstructured":"Ren F, Matsumoto K (2015) Semi-automatic creation of youth slang corpus and its application to affective computing. IEEE Trans Affect Comput 7(2):176\u2013189. https:\/\/doi.org\/10.1109\/TAFFC.2015.2457915","journal-title":"IEEE Trans Affect Comput"},{"key":"2175_CR30","doi-asserted-by":"publisher","unstructured":"Saitoh T, Konishi R (2010) Profile lip reading for vowel and word recognition. In: 2010 20th International conference on pattern recognition, pp 1356\u20131359. https:\/\/doi.org\/10.1109\/ICPR.2010.335","DOI":"10.1109\/ICPR.2010.335"},{"key":"2175_CR31","doi-asserted-by":"publisher","unstructured":"Sulistijono IA, Baiqunni HH, Darojah Z et al (2014) Vowel recognition system of Lipsynchrobot in lips gesture using neural network. In: 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp 1751\u20131756. https:\/\/doi.org\/10.1109\/FUZZ-IEEE.2014.6891843","DOI":"10.1109\/FUZZ-IEEE.2014.6891843"},{"key":"2175_CR32","doi-asserted-by":"publisher","unstructured":"Sun Y, Wang X, Tang X (2013) Deep convolutional network cascade for facial point detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3476\u20133483. https:\/\/doi.org\/10.1109\/CVPR.2013.446","DOI":"10.1109\/CVPR.2013.446"},{"issue":"2","key":"2175_CR33","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1109\/MRA.2016.2515018","volume":"23","author":"IM Verner","year":"2016","unstructured":"Verner IM, Polishuk A, Krayner N (2016) Science class with RoboThespian: using a robot teacher to make science fun and engage students. IEEE Robot Autom Mag 23(2):74\u201380. https:\/\/doi.org\/10.1109\/MRA.2016.2515018","journal-title":"IEEE Robot Autom Mag"},{"issue":"1","key":"2175_CR34","first-page":"31","volume":"19","author":"J Yan","year":"1998","unstructured":"Yan J (1998) Research on the viseme of chinese phonetics. Comput Eng Des 19(1):31\u201334 (in Chinese)","journal-title":"Comput Eng Des"},{"key":"2175_CR35","doi-asserted-by":"publisher","unstructured":"You ZJ, Shen CY, Chang C W et al (2006) A robot as a teaching assistant in an English class. In: Sixth IEEE international conference on advanced learning technologies (ICALT'06), pp 87\u201391. https:\/\/doi.org\/10.1109\/ICALT.2006.1652373","DOI":"10.1109\/ICALT.2006.1652373"},{"key":"2175_CR36","first-page":"44","volume":"10","author":"H Zeng","year":"2013","unstructured":"Zeng H, Hu D, Hu Z (2013) Simple analyzing on matching mechanism between Chinese speech and mouth shape. Audio Eng 10:44\u201348 (in Chinese)","journal-title":"Audio Eng"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-020-02175-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12652-020-02175-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-020-02175-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T15:44:54Z","timestamp":1666107894000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12652-020-02175-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,11]]},"references-count":36,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2022,11]]}},"alternative-id":["2175"],"URL":"https:\/\/doi.org\/10.1007\/s12652-020-02175-9","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"type":"print","value":"1868-5137"},{"type":"electronic","value":"1868-5145"}],"subject":[],"published":{"date-parts":[[2020,6,11]]},"assertion":[{"value":"31 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}