{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T12:08:43Z","timestamp":1725538123209},"publisher-location":"Berlin, Heidelberg","reference-count":25,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642046964"},{"type":"electronic","value":"9783642046971"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-04697-1_13","type":"book-chapter","created":{"date-parts":[[2009,9,16]],"date-time":"2009-09-16T00:50:54Z","timestamp":1253062254000},"page":"133-144","source":"Crossref","is-referenced-by-count":0,"title":["Two-Level Bimodal Association for Audio-Visual Speech Recognition"],"prefix":"10.1007","author":[{"given":"Jong-Seok","family":"Lee","sequence":"first","affiliation":[]},{"given":"Touradj","family":"Ebrahimi","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"13_CR1","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/6046.985551","volume":"4","author":"C.C. Chibelushi","year":"2002","unstructured":"Chibelushi, C.C., Deravi, F., Mason, J.S.D.: A Review of Speech-Based Bimodal Recognition. IEEE Trans. Multimedia\u00a04, 23\u201337 (2002)","journal-title":"IEEE Trans. Multimedia"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Bregler, C., Konig, Y.: \u2018Eigenlips\u2019 for Robust Speech Recognition. In: Proc. ICASSP, Adelaide, Australia, pp. 669\u2013672 (1994)","DOI":"10.1109\/ICASSP.1994.389567"},{"key":"13_CR3","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/S0167-6393(98)00056-9","volume":"26","author":"A. Rogozan","year":"1998","unstructured":"Rogozan, A., Del\u00e9glise, P.: Adaptive Fusion of Acoustic and Visual Sources for Automatic Speech Recognition. Speech Commun.\u00a026, 149\u2013161 (1998)","journal-title":"Speech Commun."},{"key":"13_CR4","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/6046.865479","volume":"2","author":"S. Dupont","year":"2000","unstructured":"Dupont, S., Luettin, J.: Audio-Visual Speech Modeling for Continuous Speech Recognition. IEEE Trans. Multimedia\u00a02, 141\u2013151 (2000)","journal-title":"IEEE Trans. Multimedia"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Lee, J.-S., Park, C.H.: Adaptive Decision Fusion for Audio-Visual Speech Recognition. In: Miheli\u010d, F., \u017dibert, J. (eds.) Speech Recognition, Technologies and Applications, I-Tech, Vienna Austria, pp. 275\u2013296 (2008a)","DOI":"10.5772\/6364"},{"key":"13_CR6","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1075\/z.99.32ben","volume-title":"The Structure of Multimodal Dialogue II","author":"C. Beno\u00eet","year":"2000","unstructured":"Beno\u00eet, C.: The Intrinsic Bimodality of Speech Communication and the Synthesis of Talking Faces. In: Taylor, M.M., Nel, F., Bouwhuis, D. (eds.) The Structure of Multimodal Dialogue II, pp. 485\u2013502. John Benjamins, Amsterdam (2000)"},{"key":"13_CR7","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.inffus.2003.07.001","volume":"5","author":"G.F. Meyer","year":"2004","unstructured":"Meyer, G.F., Mullligan, J.B., Wuerger, S.M.: Continuous Audio-Visual Digit Recognition using N-Best Decision Fusion. Information Fusion\u00a05, 91\u2013101 (2004)","journal-title":"Information Fusion"},{"key":"13_CR8","doi-asserted-by":"publisher","first-page":"4065","DOI":"10.1121\/1.2195091","volume":"119","author":"B. Conrey","year":"2006","unstructured":"Conrey, B., Pisoni, D.B.: Auditory-Visual Speech Perception and Synchrony Detection for Speech and Nonspeech Signals. J. Acoust. Soc. Amer.\u00a0119, 4065\u20134073 (2006)","journal-title":"J. Acoust. Soc. Amer."},{"key":"13_CR9","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1109\/TMM.2004.827503","volume":"6","author":"J.W. Fisher III","year":"2004","unstructured":"Fisher III, J.W., Darrell, T.: Speaker Association with Signal-Level Audiovisual Fusion. IEEE Trans. Multimedia\u00a06, 406\u2013413 (2004)","journal-title":"IEEE Trans. Multimedia"},{"key":"13_CR10","doi-asserted-by":"publisher","first-page":"1396","DOI":"10.1109\/TMM.2007.906583","volume":"9","author":"M.E. Sargin","year":"2007","unstructured":"Sargin, M.E., Yemez, Y., Erzin, E., Tekalp, A.M.: Audiovisual Synchronization and Fusion using Canonical Correlation Analysis. IEEE Trans. Multimedia\u00a09, 1396\u20131403 (2007)","journal-title":"IEEE Trans. Multimedia"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Bredin, H., Chollet, G.: Audiovisual Speech Synchrony Measure: Application to Biometrics. EURASIP J. Advances in Signal Processing 2007, 11 pages, Article ID 70186 (2007)","DOI":"10.1155\/2007\/70186"},{"key":"13_CR12","first-page":"814","volume-title":"Advances in Neural Information Processing Systems","author":"M. Slaney","year":"2001","unstructured":"Slaney, M., Covell, M.: FaceSync: A Linear Operator for Measuring Synchronization of Video Facial Images and Audio Tracks. In: Leen, T.K., Dietterich, T.G., Tresp, V. (eds.) Advances in Neural Information Processing Systems, vol.\u00a013, pp. 814\u2013820. MIT Press, Cambridge (2001)"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Eveno, N., Besacier, L.: Co-Inertia Analysis for \u201cLiveness\u201d Test in Audio-Visual Biometrics. In: Proc. Int. Symposium on Image and Signal Processing and Analysis, Zagreb, Croatia, pp. 257\u2013261 (2005)","DOI":"10.1109\/ISPA.2005.195419"},{"key":"13_CR14","volume-title":"Spoken Language Processing: A Guide to Theory, Algorithm, and System Development","author":"X. Huang","year":"2001","unstructured":"Huang, X., Acero, A., Hon, H.-W.: Spoken Language Processing: A Guide to Theory, Algorithm, and System Development. Prentice Hall, Upper Saddle River (2001)"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Lee, J.-S., Park, C.H.: Training Hidden Markov Models by Hybrid Simulated Annealing for Visual Speech Recognition. In: Proc. IEEE Int. Conf. Systems, Man, Cybernetics, Taipei, Taiwan, pp. 198\u2013202 (2006)","DOI":"10.1109\/ICSMC.2006.384382"},{"key":"13_CR16","unstructured":"Hermansky, H.: Exploring Temporal Domain for Robustness in Speech Recognition. In: Proc. Int. Congress on Acoustics, Trondheim, Norway, pp. 61\u201364 (1995)"},{"key":"13_CR17","unstructured":"Hardoon, D.R., Szedmak, S., Shawe-Taylor, J.: Canonical Correlation Analysis: An Overview with Application to Learning Methods. Dept. Comput. Sci., Univ. London, UK, Tech. Rep. CSD-TR-03-02 (2003)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Gopinath, R.A.: Maximum Likelihood Modeling with Gaussian Distributions for Classification. In: Proc. ICASSP, Seattle, USA, pp. 661\u2013664 (1998)","DOI":"10.1109\/ICASSP.1998.675351"},{"key":"13_CR19","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TMM.2008.922789","volume":"10","author":"J.-S. Lee","year":"2008","unstructured":"Lee, J.-S., Park, C.H.: Robust Audio-Visual Speech Recognition based on Late Integration. IEEE Trans. Multimedia\u00a010, 767\u2013779 (2008b)","journal-title":"IEEE Trans. Multimedia"},{"key":"13_CR20","unstructured":"Lewis, T.W., Powers, D.M.W.: Sensor Fusion Weighting Measures in Audio-Visual Speech Recognition. In: Proc. 27th Australasian Conf. Computer Science, Dunedin, New Zealand, pp. 305\u2013314 (2004)"},{"key":"13_CR21","first-page":"851","volume-title":"Advances in Neural Information Processing Systems","author":"J.R. Movellan","year":"1995","unstructured":"Movellan, J.R.: Visual Speech Recognition with Stochastic Networks. In: Tesauro, G., Touretzky, D., Leen, T. (eds.) Advances in Neural Information Processing Systems, vol.\u00a07, pp. 851\u2013858. MIT Press, Cambridge (1995)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Chibelushi, C.C., Gandon, S., Mason, J.S.D., Deravi, F., Johnston, R.D.: Design Issues for a Digital Audio-Visual Integrated Database. In: Proc. IEE Colloq. Integrated Audio-Visual Processing for Recognition, Synthesis, Communication, London, UK, pp. 7\/1\u20137\/7 (1996)","DOI":"10.1049\/ic:19961151"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Pigeon, S., Vandendrope, L.: The M2VTS Multimodal Face Database (Release 1.00). In: Proc. Int. Conf. Audio- and Video-based Biometric Authentication, Crans-Montana, Switzerland, pp. 403\u2013409 (1997)","DOI":"10.1007\/BFb0016021"},{"key":"13_CR24","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"V. Varga","year":"1993","unstructured":"Varga, V., Steeneken, H.J.M.: Assessment for Automatic Speech Recognition: II. NOISEX 1992: A Database and an Experiment to Study the Effect of Additive Noise on Speech Recognition Systems. Speech Commun.\u00a012, 247\u2013251 (1993)","journal-title":"Speech Commun."},{"key":"13_CR25","first-page":"96","volume":"15","author":"B. Rivet","year":"2007","unstructured":"Rivet, B., Girin, L., Jutten, C.: Mixing Audiovisual Speech Processing and Blind Source Separation for the Extraction of Speech Signals from Convolutive Mixtures. IEEE Trans. Multimedia\u00a015, 96\u2013108 (2007)","journal-title":"IEEE Trans. Multimedia"}],"container-title":["Lecture Notes in Computer Science","Advanced Concepts for Intelligent Vision Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-04697-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,22]],"date-time":"2019-05-22T12:19:22Z","timestamp":1558527562000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-04697-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642046964","9783642046971"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-04697-1_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}