{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T08:40:22Z","timestamp":1737621622547,"version":"3.33.0"},"publisher-location":"Berlin, Heidelberg","reference-count":54,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540773467"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-77347-4_2","type":"book-chapter","created":{"date-parts":[[2007,12,6]],"date-time":"2007-12-06T11:27:29Z","timestamp":1196940449000},"page":"28-56","source":"Crossref","is-referenced-by-count":1,"title":["Some Experiments in Audio-Visual Speech Processing"],"prefix":"10.1007","author":[{"given":"G.","family":"Chollet","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Landais","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T.","family":"Hueber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"H.","family":"Bredin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Mokbel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P.","family":"Perrot","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L.","family":"Zouari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"2_CR1","series-title":"NATO ASI Series, Series F: Computer and System Sciences","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1007\/978-3-642-60087-6_32","volume-title":"Computational Models of Speech Pattern Processing","author":"G. Chollet","year":"1999","unstructured":"Chollet, G., Cernocky, J., Constantinescu, A., Deligne, S., Bimbot, F.: Towards ALISP: a Proposal for Automatic Language Independent Speech Processing. In: Computational Models of Speech Pattern Processing. NATO ASI Series, Series F: Computer and System Sciences, vol.\u00a0169, pp. 375\u2013387. Springer, Heidelberg (1999)"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Bimbot, F., Chollet, G., Deleglise, P., Montaci\u00e9, C.: Temporal Decomposition and Acoustic-Phonetic Decoding of Speech. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 445\u2013448 (1988)","DOI":"10.1109\/ICASSP.1988.196614"},{"key":"2_CR3","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-3626-0","volume-title":"Vector Quantization and Signal Compression","author":"A. Gersho","year":"1992","unstructured":"Gersho, A., Gray, R.: Vector Quantization and Signal Compression. Kluwer, Boston (1992)"},{"key":"2_CR4","unstructured":"Petrovska-Delacretaz, D., Chollet, G.: Searching Through a Speech Memory for Efficient Coding, Recognition and Synthesis. In: Braun, A., Masthoff, H. (eds.) Phonetics and its Applications. Festschrift for Jens-Peter K\u00f6ster on the occasion of his 60th birthday, pp. 453\u2013464. Franz Steiner Verlag (2002)"},{"issue":"1","key":"2_CR5","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/34.982883","volume":"24","author":"M.H. Yang","year":"2002","unstructured":"Yang, M.H., Kriegman, D., Ahuja, N.: Detecting Faces in Images: a Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence\u00a024(1), 34\u201358 (2002)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"2_CR6","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P.A. Viola","year":"2002","unstructured":"Viola, P.A., Jones, M.J.: Robust Real-Time Object Detection. International Journal of Computer Vision\u00a057(2), 137\u2013154 (2002)","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"2_CR7","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.cviu.2004.07.014","volume":"98","author":"I. Fasel","year":"2004","unstructured":"Fasel, I., Fortenberry, B., Movellan, J.: A Generative Framework for Real-Time Object Detection and Classification. Computer Vision and Image Understanding\u00a098(1), 182\u2013210 (2004)","journal-title":"Computer Vision and Image Understanding"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Santana, M.C., Navarro, J.L., Su\u00e1rez, O.D., Martel, A.F.: Multiple Face Detection at Different Resolutions for Perceptual User Interfaces. In: 2nd Iberian Conference on Pattern Recognition and Image Analysis, Estoril, Portugal (June 2005)","DOI":"10.1007\/11492429_54"},{"issue":"4","key":"2_CR9","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/BF00133570","volume":"1","author":"M. Kass","year":"1988","unstructured":"Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. International Journal of Computer Vision\u00a01(4), 321\u2013331 (1988)","journal-title":"International Journal of Computer Vision"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Davis, S., Mermelstein, P.: Comparaison of Parametric Representations of Monosyllabic Word Recognition in Continuously Spoken Sentences. In: IEEE International Conference on Acoustics, Speech ans Signal Processing, pp. 357\u2013366 (April 1980)","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"2_CR11","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H. Hermansky","year":"1990","unstructured":"Hermansky, H.: Perceptual Linear Predictive (plp) Analysis of Speech. J. Acoust. Soc. America\u00a087, 1738\u20131752 (1990)","journal-title":"J. Acoust. Soc. America"},{"issue":"2","key":"2_CR12","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"D. Lowe","year":"2004","unstructured":"Lowe, D.: Distinctive Image Features from Scale-Invariant Keypoints. Int. Journal of Computer Vision\u00a060(2), 91\u2013110 (2004)","journal-title":"Int. Journal of Computer Vision"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Mikolajczyk, K., Schmid, C.: A Performance Evaluation of Local Descriptors. IEEE trans on Pattern Analysis and Machine Intelligence 27(10) (2005)","DOI":"10.1109\/TPAMI.2005.188"},{"key":"2_CR14","unstructured":"Witkin, A.: Scale-Space Filtering. In: Proceedings of the 8th International Joint Conference on Artificial Intelligence, pp. 1019\u20131022 (1983)"},{"key":"2_CR15","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/BF00336961","volume":"50","author":"J. Koenderink","year":"1984","unstructured":"Koenderink, J.: The Structure of Images. Biological Cybernetics\u00a050, 363\u2013370 (1984)","journal-title":"Biological Cybernetics"},{"issue":"1","key":"2_CR16","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1162\/jocn.1991.3.1.71","volume":"3","author":"M. Turk","year":"1991","unstructured":"Turk, M., Pentland, A.: Eigenfaces for Recognition. Journal of Cognitive Neuroscience\u00a03(1), 71\u201386 (1991)","journal-title":"Journal of Cognitive Neuroscience"},{"issue":"3","key":"2_CR17","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1109\/34.667881","volume":"20","author":"J. Kittler","year":"1998","unstructured":"Kittler, J., Hatef, M., Duin, R., Matas, J.: On combining classifiers. IEEE Trans. Pattern Anal. Mach. Intell.\u00a020(3), 226\u2013239 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR18","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1111\/j.1365-2427.1994.tb01741.x","volume":"31","author":"S. Dol\u00e9dec","year":"1994","unstructured":"Dol\u00e9dec, S., Chessel, D.: Co-Inertia Analysis: an Alternative Method for Studying Species-Environment Relationships. Freshwater Biology\u00a031, 277\u2013294 (1994)","journal-title":"Freshwater Biology"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Reynolds, D., Quatieri, T., Dunn, R.: Speaker Verification Using Adapted Gaussian Mixture Models. Digital Signal Processing\u00a0(10), 19\u201341 (2000)","DOI":"10.1006\/dspr.1999.0361"},{"issue":"4","key":"2_CR20","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1109\/89.917680","volume":"9","author":"C. Mokbel","year":"2001","unstructured":"Mokbel, C.: Online Adaptation of HMMs to Real-Life Conditions: A Unified Framework. IEEE Trans. On Speech and Audio Processing\u00a09(4), 342\u2013357 (2001)","journal-title":"IEEE Trans. On Speech and Audio Processing"},{"issue":"2","key":"2_CR21","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L. Rabiner","year":"1989","unstructured":"Rabiner, L.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE\u00a077(2), 257\u2013286 (1989)","journal-title":"Proceedings of the IEEE"},{"key":"2_CR22","volume-title":"Issues in Visual and Audio-Visual Speech Processing","author":"G. Potamianos","year":"2004","unstructured":"Potamianos, G., Neti, C., Luettin, J., Matthews, I.: Audio-Visual Automatic Speech Recognition: An Overview. In: Bailly, G., Vatikiotis-Bateson, E., Perrier, P. (eds.) Issues in Visual and Audio-Visual Speech Processing, MIT Press, Cambridge (2004)"},{"key":"2_CR23","unstructured":"Argones-R\u00faa, E., Garc\u00eda-Mateo, C., Bredin, H., Chollet, G.: Aliveness Detection using Coupled Hidden Markov Models. In: SWB 2007. First Spanish Workshop on Biometrics, Girona, Spain (June 2007)"},{"key":"2_CR24","unstructured":"Brand, M., Oliver, N., Pentland, A.: Coupled hidden markov models for complex action recognition (1996)"},{"key":"2_CR25","unstructured":"Misra, H.: Multi-stream processing for noise robust speech recognition. PhD thesis, Lausanne (2006)"},{"key":"2_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/3-540-44887-X_74","volume-title":"Audio-and Video-Based Biometrie Person Authentication","author":"E. Bailly-Bailli\u00e8re","year":"2003","unstructured":"Bailly-Bailli\u00e8re, E., Bengio, S., Bimbot, F., Hamouz, M., Kittler, J., Mari\u00e9thoz, J., Matas, J., Messer, K., Popovici, V., Por\u00e9e, F., Ruiz, B., Thiran, J.P.: The BANCA and Evaluation Protocol. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol.\u00a02688, pp. 625\u2013638. Springer, Heidelberg (2003)"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Hazen, T.: Visual Model Structures and Synchrony Constraints for Audio-Visual Speech Recognition. IEEE Transactions on Audio, Speech and Language Processing 14(3) (2006)","DOI":"10.1109\/TSA.2005.857572"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Dupont, S., Luettin, J.: Audio-Visual Speech Modeling for Continuous Speech Recognition. IEEE Transcations on Multimedia 2(3) (2000)","DOI":"10.1109\/6046.865479"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Potamianos, G., Neti, C., Gravier, G., Garg, A., Senior, A.: Recent Advances in the Automatic Recognition of Audiovisual Speech. IEEE 91(9) (2003)","DOI":"10.1109\/JPROC.2003.817150"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Chu, S., Huang, T.: Audio Visual Speech Modelling using Coupled Hidden Markov Models. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2009\u20132012 (2002)","DOI":"10.1109\/ICASSP.2002.1006166"},{"issue":"4","key":"2_CR31","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1109\/TNN.2002.1021886","volume":"13","author":"S. Nakamura","year":"2002","unstructured":"Nakamura, S.: Statistical Multimodal Integration for Audio-Visual Speech Processing. IEEE Transactions on Neural Networks\u00a013(4), 854\u2013866 (2002)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"2_CR32","unstructured":"Brugger, F., Zouari, L., Bredin, H., Amehraye, A., Chollet, G., Pastor, D., Ni, Y.: Reconnaissance Audio-Visuelle de la Parole par VMike. In: JEP 2006. XXVI\u00e8me Journ\u00e9s d\u2019\u00c9tude sur la Parole, Dinard, France, pp. 417\u2013420 (June 2006)"},{"key":"2_CR33","unstructured":"The\u00a0NoiseX Database: http:\/\/spib.rice.edu\/spib"},{"key":"2_CR34","unstructured":"Young, S., Evermann, G., Kershaw, D., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., Woodland, P.: The HTK Book (for HTK Version 3.2). Cambridge University Engineering Department (December 2002)"},{"key":"2_CR35","volume-title":"Handbook of Multibiometrics","author":"A.A. Ross","year":"2006","unstructured":"Ross, A.A., Nandakumar, K., Jain, A.K.: Handbook of Multibiometrics. Springer, Heidelberg (2006)"},{"issue":"1309","key":"2_CR36","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1098\/rspb.1991.0045","volume":"244","author":"G. Scott","year":"1991","unstructured":"Scott, G., Longuet-Higgins, H.: An Algorithm for Associating the Features of Two Images. Proc. of the Royal Society of London. Series B. Biological Sciences\u00a0244(1309), 21\u201326 (1991)","journal-title":"Proc. of the Royal Society of London. Series B. Biological Sciences"},{"key":"2_CR37","unstructured":"Pilu, M.: Uncalibrated Stereo Correspondence by Singular Value Decomposition. Technical Report HPL-97-96, Digital Media Department HP Laboratories (1997)"},{"key":"2_CR38","unstructured":"Delponte, E., Isgr, F., Odone, F., Verri, A.: SVD-Matching using SIFT Features. In: Proc. of the Int. Conf. on Vision, Video and Graphics, pp. 125\u2013132 (2005)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Bicego, M., Lagorio, A., Grosso, E., Tistarelli, M.: On the Use of SIFT Features for Face Authentication. In: CVPRW. Conf. on Computer Vision and Pattern Recognition Workshop (2006)","DOI":"10.1109\/CVPRW.2006.149"},{"key":"2_CR40","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3877.001.0001","volume-title":"The Interpretation of Visual Motion","author":"S. Ullman","year":"1979","unstructured":"Ullman, S.: The Interpretation of Visual Motion. MIT Press, Cambridge, MA (1979)"},{"key":"2_CR41","volume-title":"Matrix Computations","author":"G. Golub","year":"1996","unstructured":"Golub, G., Loan, C.V.: Matrix Computations, 3rd edn. The Johns Hopkins University Press, Baltimore, MD (1996)","edition":"3"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Pilu, M.: A Direct Method for Stereo Correspondence based on Singular Value Decomposition. In: Proceedings of CVPR, pp. 261\u2013266 (1997)","DOI":"10.1109\/CVPR.1997.609330"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Bredin, H., Miguel, A., Witten, I.H., Chollet, G.: Detecting Replay Attacks in Audiovisual Identity Verification. In: ICASSP 2006. 31st IEEE International Conference on Acoustics, Speech, and Signal Processing, Toulouse, France, vol.\u00a01, pp. 621\u2013624 (May 2006)","DOI":"10.1109\/ICASSP.2006.1660097"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Abe, M., Nakamura, S., Shikano, K., Kuwabara, H.: Voice Conversion through Vector Quantization. In: International Conference on Acoustics, Speech and Signal Processing (1988)","DOI":"10.1109\/ICASSP.1988.196671"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Capp\u00e9, O., Stylianou, Y., Moulines, E.: Statistical Methods for Voice Quality Transformation. In: EUROSPEECH (1995)","DOI":"10.21437\/Eurospeech.1995-121"},{"key":"2_CR46","unstructured":"Sundermann, D., Hge, H., Bonafonte, A., Ney, H., Black, A., Narayanan, S.: Text-Independent Voice Conversion Based on Unit Selection. In: International Conference on Acoustics, Speech and Signal Processing, Toulouse, France (2006)"},{"key":"2_CR47","unstructured":"Genoud, D., Chollet, G.: Voice Transformations: Some Tools for the Imposture of Speaker Verification Systems, pp. 375\u2013387 Franz Steiner Verlag (1999)"},{"key":"2_CR48","unstructured":"Stylianou, Y., Capp\u00e9, O.: A System for Voice Conversion Based on Probabilistic Classification and a Harmonic Plus Noise Model. In: International Conference on Acoustics, Speech and Signal Processing (1998)"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Valbret, H., Moulines, E., Tubach, J.: Voice Transformation Using TDPSOLA Technique. In: International Conference on Acoustics, Speech and Signal Processing (1992)","DOI":"10.1109\/ICASSP.1992.225951"},{"key":"2_CR50","unstructured":"Perrot, P., Aversano, G., Blouet, R., Charbit, M., Chollet, G.: Voice Forgery using ALISP. In: International Conference on Acoustics, Speech and Signal Processing (2005)"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Jou, S.C.S., Schultz, T., Waibel, A.: Continuous Electromyographic Speech Recognition with a Multi-Stream Decoding Architecture. In: International Conference on Communication Audio and Speech Processing, Honolulu, Hawaii (April 2007)","DOI":"10.1109\/ICASSP.2007.366934"},{"key":"2_CR52","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1145\/1107548.1107577","volume-title":"sOc-EUSAI 2005","author":"P. Heracleous","year":"2005","unstructured":"Heracleous, P., Nakajima, Y., Saruwatari, H., Shikano, K.: A Tissue-Conductive Acoustic Sensor Applied in Speech Recognition for Privacy. In: sOc-EUSAI 2005. Proceedings of the 2005 joint conference on Smart objects and ambient intelligence, pp. 93\u201397. ACM Press, New York (2005)"},{"key":"2_CR53","unstructured":"Denby, B., Oussar, Y., Dreyfus, G., Stone, M.: Prospect for a Silent Speech Interface Using Ultrasound Imaging. In: International Conference on Acoustics, Speech and Signal Processing, Toulouse, France (2006)"},{"key":"2_CR54","unstructured":"Hueber, T., Chollet, C., Denby, B., Stone, M., Zouari, L.: Ouisper: Corpus Based Synthesis Driven by Articulatory Data. In: International Conference on Phonetic Science (to appear, 2007)"}],"container-title":["Lecture Notes in Computer Science","Advances in Nonlinear Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-77347-4_2.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T08:11:24Z","timestamp":1737619884000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-77347-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540773467"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-77347-4_2","relation":{},"subject":[]}}