{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T13:40:44Z","timestamp":1760708444125},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2012,6,21]],"date-time":"2012-06-21T00:00:00Z","timestamp":1340236800000},"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":[[2013,8]]},"DOI":"10.1007\/s11042-012-1128-7","type":"journal-article","created":{"date-parts":[[2012,6,20]],"date-time":"2012-06-20T15:56:24Z","timestamp":1340207784000},"page":"521-541","source":"Crossref","is-referenced-by-count":16,"title":["Clustering Persian viseme using phoneme subspace for developing visual speech application"],"prefix":"10.1007","volume":"65","author":[{"given":"Mohammad","family":"Aghaahmadi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad Mahdi","family":"Dehshibi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Azam","family":"Bastanfard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahmood","family":"Fazlali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,6,21]]},"reference":[{"key":"1128_CR1","doi-asserted-by":"crossref","unstructured":"B\u00e4lter O, Engwall O, \u00d6ster A-M, Kjellstr\u00f6m H (2005) Wizard-of-Oz test of ARTUR: a computer-based speech training system with articulation correction. Paper presented at the proceedings of the 7th international ACM SIGACCESS conference on computers and accessibility, Baltimore, MD, USA","DOI":"10.1145\/1090785.1090795"},{"key":"1128_CR2","first-page":"1080","volume-title":"Lecture notes in computer science, vol 5879","author":"A Bastanfard","year":"2009","unstructured":"Bastanfard A, Aghaahmadi M, Kelishami A, Fazel M, Moghadam M (2009) Persian viseme classification for developing visual speech training application advances in multimedia information processing\u2014PCM 2009. In: Muneesawang P, Wu F, Kumazawa I, Roeksabutr A, Liao M, Tang X (eds) Lecture notes in computer science, vol 5879. Springer, Berlin, pp 1080\u20131085"},{"key":"1128_CR3","doi-asserted-by":"crossref","unstructured":"Bastanfard A, Fazel M, Kelishami AA, Aghaahmadi M (2009) A comprehensive audio-visual corpus for teaching sound persian phoneme articulation. Paper presented at the Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics, San Antonio, TX, USA","DOI":"10.1109\/ICSMC.2009.5346591"},{"key":"1128_CR4","first-page":"284","volume-title":"Lecture notes in computer science, vol 5916","author":"A Bastanfard","year":"2010","unstructured":"Bastanfard A, Fazel M, Kelishami A, Aghaahmadi M (2010) The Persian linguistic based audio-visual data corpus, AVA II, considering coarticulation. Advances in multimedia modeling. In: Boll S, Tian Q, Zhang L, Zhang Z, Chen Y-P (eds) Lecture notes in computer science, vol 5916. Springer, Berlin, pp 284\u2013294"},{"key":"1128_CR5","doi-asserted-by":"crossref","unstructured":"Bastanfard A, Rezaei NA, Mottaghizadeh M, Fazel M (2010) A novel multimedia educational speech therapy system for hearing impaired children. Paper presented at the proceedings of the advances in multimedia information processing, and 11th Pacific Rim conference on Multimedia: Part II, Shanghai, China","DOI":"10.1007\/978-3-642-15696-0_65"},{"key":"1128_CR6","first-page":"585","volume":"14","author":"M Belkin","year":"2001","unstructured":"Belkin M, Niyogi P (2001) Laplacian eigenmaps and spectral techniques for embedding and clustering. Adv Neural Inf Process Syst 14:585\u2013591","journal-title":"Adv Neural Inf Process Syst"},{"issue":"4","key":"1128_CR7","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1044\/jshr.2504.600","volume":"25","author":"A-P Benguerel","year":"1984","unstructured":"Benguerel A-P, Pichora-Fuller MK (1984) Coarticulation effects in lipreading. J Speech Hear Res 25(4):600\u2013607","journal-title":"J Speech Hear Res"},{"issue":"1","key":"1128_CR8","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1023\/A:1008166717597","volume":"38","author":"T Ezzat","year":"2000","unstructured":"Ezzat T, Poggio T (2000) Visual speech synthesis by morphing visemes. Int J Comput Vision 38(1):45\u201357","journal-title":"Int J Comput Vision"},{"key":"1128_CR9","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1044\/jshr.1104.796","volume":"11","author":"CG Fisher","year":"1968","unstructured":"Fisher CG (1968) Confusions among visually perceived consonants. J Speech Hear Res 11:796\u2013804","journal-title":"J Speech Hear Res"},{"key":"1128_CR10","unstructured":"Garcia C, Zikos G, Tziritas G (1998) A wavelet-based framework for face recognition. Paper presented at the workshop on advances in facial image analysis and recognition technology, 5th European conference on computer vision"},{"key":"1128_CR11","doi-asserted-by":"crossref","unstructured":"Harris C, Stephens M (1988) A combined corner and edge detector. Paper presented at the proceedings of the 4th Alvey vision conference","DOI":"10.5244\/C.2.23"},{"issue":"1","key":"1128_CR12","first-page":"100","volume":"28","author":"JA Hartigan","year":"1977","unstructured":"Hartigan JA, Wong MA (1977) Algorithm AS 136: a K-means clustering algorithm. J R Stat Soc Ser C (Appl Stat) 28(1):100\u2013108","journal-title":"J R Stat Soc Ser C (Appl Stat)"},{"issue":"2","key":"1128_CR13","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/BF00429747","volume":"3","author":"C Henton","year":"1996","unstructured":"Henton C, Edelman B (1996) Generating and manipulating emotional synthetic speech on a personal computer. Multimed Tools Appl 3(2):105\u2013125","journal-title":"Multimed Tools Appl"},{"key":"1128_CR14","unstructured":"http:\/\/www.ldc.upenn.edu\/Catalog\/CatalogEntry.jsp?catalogId=LDC2009V01 Audiovisual database of spoken American English. Accessed 13th December 2011"},{"issue":"301","key":"1128_CR15","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1080\/01621459.1963.10500845","volume":"58","author":"H Joe","year":"1963","unstructured":"Joe H, Ward J (1963) Hierarchical grouping to optimize an objective function. J Am Stat Assoc 58(301):236\u2013244","journal-title":"J Am Stat Assoc"},{"key":"1128_CR16","unstructured":"Karabalkan H, Erdo\u011fan H (2007) Audio-visual speech recognition in vehicular noise using a multi-classifier approach. Paper presented at the DSP for in-Vehicle and Mobile Systems, Istanbul, Turkey"},{"key":"1128_CR17","doi-asserted-by":"crossref","unstructured":"Kjellstrm H, Engwall O, Abdou S, Balter O (2007) Audio-visual phoneme classification for pronunciation training applications paper presented at the 8th Annual Conference of the International Speech Communication Association","DOI":"10.21437\/Interspeech.2007-294"},{"issue":"3","key":"1128_CR18","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.specom.2008.07.005","volume":"51","author":"H Kjellstr\u00f6m","year":"2009","unstructured":"Kjellstr\u00f6m H, Engwall O (2009) Audiovisual-to-articulatory inversion. Speech Commun 51(3):195\u2013209","journal-title":"Speech Commun"},{"issue":"9","key":"1128_CR19","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1109\/5.58325","volume":"78","author":"T Kohonen","year":"1990","unstructured":"Kohonen T (1990) The self-organizing map. Proc IEEE 78(9):1464\u20131480","journal-title":"Proc IEEE"},{"key":"1128_CR20","unstructured":"Kr\u0148oul Z, C\u00edsa\u0159 P, \u017delezn\u00fd M, Holas J (2005) Viseme analysis for speech-driven facial animation for Czech audio-visual speech synthesis. Paper presented at the SPECOM, Moscow, Russia"},{"issue":"1A","key":"1128_CR21","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1121\/1.1981245","volume":"51","author":"I Lehiste","year":"1972","unstructured":"Lehiste I, Shockey L (1972) Coarticulation effects in the identification of final plosives. J Acoust Soc Am 51(1A):101","journal-title":"J Acoust Soc Am"},{"key":"1128_CR22","first-page":"773","volume-title":"Lecture notes in computer science, vol 3691","author":"M Leszczynski","year":"2005","unstructured":"Leszczynski M, Skarbek W (2005) Viseme classification for talking head application computer analysis of images and patterns. In: Gagalowicz A, Philips W (eds) Lecture notes in computer science, vol 3691. Springer, Berlin, pp 773\u2013780"},{"issue":"2","key":"1128_CR23","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1121\/1.2973234","volume":"125","author":"A Lofqvist","year":"2009","unstructured":"Lofqvist A (2009) Vowel-to-vowel coarticulation in Japanese: the effect of consonant duration. J Acoust Soc Am 125(2):636\u2013639","journal-title":"J Acoust Soc Am"},{"issue":"2","key":"1128_CR24","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1007\/s11042-009-0344-2","volume":"49","author":"M Mansoorizadeh","year":"2010","unstructured":"Mansoorizadeh M, Charkari NM (2010) Multimodal information fusion application to human emotion recognition from face and speech. Multimed Tools Appl 49(2):277\u2013297","journal-title":"Multimed Tools Appl"},{"key":"1128_CR25","unstructured":"Melenchon J, Simo J, Cobo G, Martinez E (2007) Objective viseme extraction and audiovisual uncertainty: estimation limits between auditory and visual modes. Paper presented at the International Conference on Auditory-Visual Speech Processing"},{"key":"1128_CR26","unstructured":"M\u00f6tt\u00f6nen R, Oliv\u00e9s J, Kulja J, Sams M (2000) Parameterized visual speech synthesis and its evaluation Proc. of EUSIPCO 2000, Tampere, Finland"},{"key":"1128_CR27","doi-asserted-by":"crossref","unstructured":"Nefian AV, Liang L, Pi X, Liu X, Mao C, Murphy K (2002) A coupled HMM for audio-visual speech recognition. In: Proceedings of ICASSP\u201802","DOI":"10.1109\/ICASSP.2002.5745027"},{"key":"1128_CR28","doi-asserted-by":"crossref","unstructured":"Potamianos G, Graf HP, Cosatto E (1998) An image transform approach for HMM based automatic lipreading. International Conference on Image Processing ICIP (3):173\u2013177","DOI":"10.1109\/ICIP.1998.999008"},{"key":"1128_CR29","unstructured":"Potamianos G, Neti C, Luettin J, Matthews I (2004) Audiovisual automatic speech recognition: an overview. Issues inb Visual and Audio-Visual Speech Processing, MIT Press"},{"key":"1128_CR30","unstructured":"Safabakhsh R, Mirzazadeh F. AUT-Talk: a farsi talking head. In: information and communication technologies, 2006. ICTTA \u201806. 2nd, 0-0 0 2006, pp 2994\u20132998"},{"issue":"1","key":"1128_CR31","first-page":"62","volume":"5","author":"W Salah","year":"2007","unstructured":"Salah W, Walid M, Abdelmajid H (2007) Lip localization and viseme classification for visual speech recognition. Int J Comput Inf Sci 5(1):62\u201375","journal-title":"Int J Comput Inf Sci"},{"issue":"5","key":"1128_CR32","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1162\/089976698300017467","volume":"10","author":"B Scholkopf","year":"1998","unstructured":"Scholkopf B, Smola AJ, Muller K-R (1998) Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput 10(5):1299\u20131319","journal-title":"Neural Comput"},{"issue":"1","key":"1128_CR33","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/BF00403084","volume":"3","author":"R Shaw","year":"1996","unstructured":"Shaw R, Laplante PA, Salinas J, Riccone R (1996) A multimedia speech learning system for the hearing impaired. Multimed Tools Appl 3(1):55\u201370","journal-title":"Multimed Tools Appl"},{"key":"1128_CR34","doi-asserted-by":"crossref","unstructured":"Tiddeman B, Perrett D (2002) Prototyping and transforming visemes for animated speech. Paper presented at the proceedings of the computer animation","DOI":"10.1109\/CA.2002.1017545"},{"issue":"1","key":"1128_CR35","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1162\/jocn.1991.3.1.71","volume":"3","author":"M Turk","year":"1991","unstructured":"Turk M, Pentland A (1991) Eigenfaces for recognition. J Cogn Neurosci 3(1):71\u201386","journal-title":"J Cogn Neurosci"},{"key":"1128_CR36","doi-asserted-by":"crossref","unstructured":"Visser M, Poel M, Nijholt A (1999) Classifying visemes for automatic lipreading. Paper presented at the Proceedings of the Second International Workshop on Text, Speech and Dialogue","DOI":"10.1007\/3-540-48239-3_65"},{"issue":"4","key":"1128_CR37","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1007\/BF01215883","volume":"1","author":"K Waters","year":"1995","unstructured":"Waters K, Levergood T (1995) DECface: a system for synthetic face applications. Multimed Tools Appl 1(4):349\u2013366","journal-title":"Multimed Tools Appl"},{"issue":"1","key":"1128_CR38","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1023\/A:1008062122135","volume":"20","author":"JJ Williams","year":"1998","unstructured":"Williams JJ, Rutledge JC, Katsaggelos AK, Garstecki DC (1998) Frame rate and viseme analysis for multimedia applications to assist speechreading. J VLSI Signal Process 20(1):7\u201323","journal-title":"J VLSI Signal Process"},{"key":"1128_CR39","unstructured":"Yu K, Jiang X, Bunke H (2002) Sentence lipreading using hidden Markov model with integrated grammar. In: Hidden Markov models. World Scientific Publishing Co., Inc., pp 161\u2013176"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-012-1128-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-012-1128-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-012-1128-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T05:15:42Z","timestamp":1642569342000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-012-1128-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,21]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,8]]}},"alternative-id":["1128"],"URL":"https:\/\/doi.org\/10.1007\/s11042-012-1128-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,6,21]]}}}