{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T23:40:10Z","timestamp":1715816410584},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,8,3]],"date-time":"2013-08-03T00:00:00Z","timestamp":1375488000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2014,11]]},"DOI":"10.1007\/s11042-013-1601-y","type":"journal-article","created":{"date-parts":[[2013,8,2]],"date-time":"2013-08-02T06:20:33Z","timestamp":1375424433000},"page":"463-489","source":"Crossref","is-referenced-by-count":12,"title":["Synthesizing English emphatic speech for multimodal corrective feedback in computer-aided pronunciation training"],"prefix":"10.1007","volume":"73","author":[{"given":"Fanbo","family":"Meng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianhong","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,8,3]]},"reference":[{"key":"1601_CR1","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/S0167-6393(96)00047-7","volume":"20","author":"SE Bou-Ghazale","year":"1996","unstructured":"Bou-Ghazale SE, Hansen JHL (1996) Generating stressed speech from neutral speech using a modified CELP vocoder. Speech Comm 20:93\u2013110, Oxford University Press","journal-title":"Speech Comm"},{"key":"1601_CR2","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1109\/89.668815","volume":"6","author":"SE Bou-Ghazale","year":"1998","unstructured":"Bou-Ghazale SE, Hansen JHL (1998) HMM-based stressed speech modeling with application to improved synthesis and recognition of isolated speech under stress. IEEE Trans Speech Audio Process 6:201\u2013216, IEEE Press","journal-title":"IEEE Trans Speech Audio Process"},{"key":"1601_CR3","doi-asserted-by":"crossref","unstructured":"Chen SW, Wang B, Xu Y (2009) Closely related languages, different ways of realizing focus. Proceedings of Interspeech","DOI":"10.21437\/Interspeech.2009-298"},{"key":"1601_CR4","unstructured":"http:\/\/www.cstr.ed.ac.uk\/projects\/festival\/"},{"key":"1601_CR5","doi-asserted-by":"crossref","unstructured":"Jia J, Zhang S, Meng FB, Wang YX, Cai LH (2011) Emotional audio-visual speech synthesis based on PAD. IEEE transactions on audio, speech, and language processing 19(3):570\u2013582","DOI":"10.1109\/TASL.2010.2052246"},{"key":"1601_CR6","unstructured":"Kominek J, Black AW (2003) CMU ARCTIC databases for speech synthesis. Tech. Rep. CMU-LTI-03-177, Carnegie Mellon University"},{"key":"1601_CR7","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1006\/csla.1995.0010","volume":"9","author":"CJ Leggetter","year":"1995","unstructured":"Leggetter CJ, Woodland PC (1995) Maximum likelihood linear regression for speaker adaptation of continuous density HMMs. Comput Speech Lang 9:171\u2013186","journal-title":"Comput Speech Lang"},{"key":"1601_CR8","volume-title":"Duration charateristics of stress and its synthesis rules on standard Chinese, report of phonetic research","author":"AJ Li","year":"1994","unstructured":"Li AJ (1994) Duration charateristics of stress and its synthesis rules on standard Chinese, report of phonetic research. CASS, Beijing"},{"key":"1601_CR9","first-page":"1239","volume":"51","author":"Y Li","year":"2011","unstructured":"Li Y, Lu YC, Xu XY, Tao JH (2011) Influence of rhythm and tone pattern on Mandarin stress perception in continuous speech. J Tsinghua Univ (Sci Technol) 51:1239\u20131243, Tsinghua University Press","journal-title":"J Tsinghua Univ (Sci Technol)"},{"key":"1601_CR10","first-page":"1171","volume":"51","author":"Y Li","year":"2011","unstructured":"Li Y, Pan SF, Tao JH (2011) HMM-based expressive speech synthesis with a flexible Mandarin stress adaptation model. J Tsinghua Univ (Sci Technol) 51:1171\u20131175, Tsinghua Unversity Press","journal-title":"J Tsinghua Univ (Sci Technol)"},{"key":"1601_CR11","doi-asserted-by":"crossref","unstructured":"Liu F (2010) Single vs double focus in English statements and yes no questions. Proceedings of Speech Prosody. ISCA Press, Chicago","DOI":"10.21437\/SpeechProsody.2010-82"},{"key":"1601_CR12","doi-asserted-by":"crossref","unstructured":"Maeno Y, Nose T, Kobayashi T, Ijim Y, Nakajima H, Mizuno H, Yoshioka O (2011) HMM-based emphatic speech synthesis using unsupervised context labeling. Proceedings of Interspeech. Oxford University, Italy, p. 1849\u20131852","DOI":"10.21437\/Interspeech.2011-45"},{"key":"1601_CR13","unstructured":"Meng H, Lo WK, Harrison AM, Lee P, Wong KH, Leung WK, Meng FB (2011) Development of automatic speech recongition and synthesis technologies to support Chinese learners of English: the CUHK experience. Proceedings of APSIPA. Cambridge University Press, Taiwan, March"},{"key":"1601_CR14","doi-asserted-by":"crossref","unstructured":"Meng FB, Wu ZY, Meng H, Jia J, Cai LH (2012) Hierarchical English emphatic speech synthesis based on HMM with limited training data. Proceedings of Interspeech. Oxford University Press","DOI":"10.21437\/Interspeech.2012-159"},{"key":"1601_CR15","doi-asserted-by":"crossref","unstructured":"Morizane K, Nakamura K, Toda T, Saruwatari H, Shikano K (2009) Emphasized speech synthesis based on hidden Markov models. Proceedsing of Speech Database and Assessments Oriental COCOSDA International Conference. IEEE Press, p. 76\u201381","DOI":"10.1109\/ICSDA.2009.5278371"},{"key":"1601_CR16","doi-asserted-by":"crossref","unstructured":"Neri A, Cucchiarini C, Strik H (2006) ASR-based corrective feedback on pronunciation: Does it really work? Proceedings of Interspeech. Pittsburgh, USA","DOI":"10.21437\/Interspeech.2006-543"},{"issue":"1","key":"1601_CR17","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1017\/S1360674306001821","volume":"10","author":"I Plag","year":"2006","unstructured":"Plag I (2006) The variability of compound stress in English: structural, semantic and analogical factors. Engl Lang Linguist 10(1):143\u2013172, Cambridge University Press","journal-title":"Engl Lang Linguist"},{"key":"1601_CR18","doi-asserted-by":"crossref","unstructured":"Raux A, Black AW (2003) A unit selection approach to F0 modeling and its application to emphasis, Proceedings of ASRU","DOI":"10.1109\/ASRU.2003.1318525"},{"key":"1601_CR19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/002383099603900101","volume":"39","author":"HH Rump","year":"1996","unstructured":"Rump HH, Collier R (1996) Focus conditions and the prominence of pitch-accented syllables. Lang Speech 39:1\u201317, MIT Press","journal-title":"Lang Speech"},{"issue":"3","key":"1601_CR20","first-page":"563","volume":"11","author":"EO Selkirk","year":"1980","unstructured":"Selkirk EO (1980) The role of prosodic categories in English word stress. Linguist Inq 11(3):563\u2013605, MIT Press","journal-title":"Linguist Inq"},{"key":"1601_CR21","unstructured":"Strangert E (2003) Emphasis by pausing. Proceedings of 15th ICPhS. Cambridge University Press, Barcelona, p. 2477\u20132480"},{"key":"1601_CR22","doi-asserted-by":"crossref","unstructured":"Tamburini F (2003) Automatic prosodic prominence detection in speech using acoustic features: an unsupervised system. Proceedings of Eurospeech. Oxford University, 129\u2013132","DOI":"10.21437\/Eurospeech.2003-81"},{"key":"1601_CR23","doi-asserted-by":"crossref","unstructured":"Tamburini F (2003) Prosodic prominence detection in speech. Proceedings of Signal Processing and its Applications. IEEE Press, p. 385\u2013388","DOI":"10.1109\/ISSPA.2003.1224721"},{"key":"1601_CR24","unstructured":"Tokuda K, Yoshimura T, Masuko T, Kobayashi T, Kitamura T (2003) Speech parameter generation algorithms for HMM-based speech synthesis. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, Istanbul, Turkey, 3:1315\u20131318"},{"key":"1601_CR25","unstructured":"Tokuda K, Zen H, Yamagishi J, Masuko T, Sako S, Black A, Nose T (2008) The HMM-based speech synthesis system (HTS) version 2.1. http:\/\/hts.sp.nitech.ac.jp\/"},{"key":"1601_CR26","doi-asserted-by":"crossref","unstructured":"Xie L, Liu ZQ (2007) Realistic mouth-synching for speech-driven talking face using articulatory modelling. IEEE Multimedia 9(3):500\u2013510","DOI":"10.1109\/TMM.2006.888009"},{"key":"1601_CR27","first-page":"335","volume":"4","author":"JP Xu","year":"2004","unstructured":"Xu JP, Chu M, Lin HE, Lu SN (2004) The influence of Chinese sentence stress on pitch and duration. Chin J Acoust 4:335\u2013339, Allerton Press","journal-title":"Chin J Acoust"},{"key":"1601_CR28","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.wocn.2004.11.001","volume":"33","author":"Y Xu","year":"2005","unstructured":"Xu Y, Xu CX (2005) Phonetic realization of focus in English declarative intonation. J Phon 33:159\u2013197, Academic Press","journal-title":"J Phon"},{"key":"1601_CR29","unstructured":"Yu K, Mairesse F, Young S (2010) Word-level emphasis modeling in HMM-based speech synthesis. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. Cambridge University Press, p. 4238\u20134241"},{"issue":"4","key":"1601_CR30","first-page":"16","volume":"16","author":"QF Zhou","year":"1996","unstructured":"Zhou QF, Cai LH (1996) Mandarin stress and its simulation in TTS system. Microcomputer 16(4):16\u201319, Microcomputer Press","journal-title":"Microcomputer"},{"issue":"3","key":"1601_CR31","first-page":"122","volume":"21","author":"WB Zhu","year":"2007","unstructured":"Zhu WB (2007) A Chinese speech synthesis system with capability of accent realizing. J Chin Inf Process 21(3):122\u2013128, Chinese Information Processing Press","journal-title":"J Chin Inf Process"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-013-1601-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-013-1601-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-013-1601-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T22:58:03Z","timestamp":1715813883000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-013-1601-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8,3]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,11]]}},"alternative-id":["1601"],"URL":"https:\/\/doi.org\/10.1007\/s11042-013-1601-y","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,8,3]]}}}