{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T06:06:15Z","timestamp":1748585175151},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540692676"},{"type":"electronic","value":"9783540692683"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11965152_3","type":"book-chapter","created":{"date-parts":[[2007,1,23]],"date-time":"2007-01-23T13:48:58Z","timestamp":1169560138000},"page":"24-35","source":"Crossref","is-referenced-by-count":4,"title":["Audio-Visual Processing in Meetings: Seven Questions and Current AMI Answers"],"prefix":"10.1007","author":[{"given":"Marc","family":"Al-Hames","sequence":"first","affiliation":[]},{"given":"Thomas","family":"Hain","sequence":"additional","affiliation":[]},{"given":"Jan","family":"Cernocky","sequence":"additional","affiliation":[]},{"given":"Sascha","family":"Schreiber","sequence":"additional","affiliation":[]},{"given":"Mannes","family":"Poel","sequence":"additional","affiliation":[]},{"given":"Ronald","family":"M\u00fcller","sequence":"additional","affiliation":[]},{"given":"Sebastien","family":"Marcel","sequence":"additional","affiliation":[]},{"given":"David","family":"van Leeuwen","sequence":"additional","affiliation":[]},{"given":"Jean-Marc","family":"Odobez","sequence":"additional","affiliation":[]},{"given":"Sileye","family":"Ba","sequence":"additional","affiliation":[]},{"given":"Herve","family":"Bourlard","sequence":"additional","affiliation":[]},{"given":"Fabien","family":"Cardinaux","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Gatica-Perez","sequence":"additional","affiliation":[]},{"given":"Adam","family":"Janin","sequence":"additional","affiliation":[]},{"given":"Petr","family":"Motlicek","sequence":"additional","affiliation":[]},{"given":"Stephan","family":"Reiter","sequence":"additional","affiliation":[]},{"given":"Steve","family":"Renals","sequence":"additional","affiliation":[]},{"given":"Jeroen","family":"van Rest","sequence":"additional","affiliation":[]},{"given":"Rutger","family":"Rienks","sequence":"additional","affiliation":[]},{"given":"Gerhard","family":"Rigoll","sequence":"additional","affiliation":[]},{"given":"Kevin","family":"Smith","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Thean","sequence":"additional","affiliation":[]},{"given":"Pavel","family":"Zemcik","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"3_CR1","unstructured":"Ba, S.O., Odobez, J.M.: Evaluation of head pose tracking algorithm in indoor environments. In: Proceedings IEEE ICME (2005)"},{"key":"3_CR2","unstructured":"Ba, S.O., Odobez, J.M.: A rao-blackwellized mixed state particle filter for head pose tracking. In: Proceedings of the ACM-ICMI Workshop on MMMP (2005)"},{"key":"3_CR3","unstructured":"BANCA: Benchmark database, http:\/\/www.ee.surrey.ac.uk\/banca"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Burger, S., MacLaren, V., Yu, H.: The ISL meeting corpus: The impact of meeting type on speech style. In: Proceedings ICSLP (2002)","DOI":"10.21437\/ICSLP.2002-140"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Cardinaux, F., Sanderson, C., Bengio, S.: Face verification using adapted generative models. In: Int. Conf. on Automatic Face and Gesture Recognition (2004)","DOI":"10.1109\/AFGR.2004.1301636"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Cardinaux, F., Sanderson, C., Marcel, S.: Comparison of MLP and GMM classifiers for face verification on XM2VTS. In: Proc. IEEE AVBPA (2003)","DOI":"10.1007\/3-540-44887-X_106"},{"key":"3_CR7","unstructured":"Carletta, J., et al.: The AMI meetings corpus. In: Proc. Symposium on Annotating and measuring Meeting Behavior (2005)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Fapso, M., Schwarz, P., Szoke, I., Smrz, P., Schwarz, M., Cernocky, J., Karafiat, M., Burget, L.: Search engine for information retrieval from speech records. In: Proceedings Computer Treatment of Slavic and East European Languages (2005)","DOI":"10.1007\/11671299_43"},{"key":"3_CR9","unstructured":"Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. In: International Conference on Machine Learning (1996)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Hain, T., Burget, L., Dines, J., Garau, G., Karafiat, M., Lincoln, M., McCowan, I., Moore, D., Wan, V., Ordelman, R., Renals, S.: The 2005 AMI system for the transcription of speech in meetings. In: Proc. of the NIST RT 2005s workshop (2005)","DOI":"10.1007\/11677482_38"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Hain, T., Dines, J., Garau, G., Karafiat, M., Moore, D., Wan, V., Ordelman, R., Renals, S.: Transcription of conference room meetings: an investigation. In: Proceedings Interspeech (2005)","DOI":"10.21437\/Interspeech.2005-543"},{"key":"3_CR12","unstructured":"Heylen, D., Nijholt, A., Reidsma, D.: Determining what people feel and think when interacting with humans and machines: Notes on corpus collection and annotation. In: Kreiner, J., Putcha, C. (eds.) Proceedings 1st California Conference on Recent Advances in Engineering Mechanics (2006)"},{"key":"3_CR13","unstructured":"Hradis, M., Juranek, R.: Real-time tracking of participants in meeting video. In: Proceedings CESCG (2006)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Janin, A., Baron, D., Edwards, J., Ellis, D., Gelbart, D., Morgan, N., Peskin, B., Pfau, T., Shriberg, E., Stolcke, A., Wooters, C.: ICSI meeting corpus. In: Proceedings IEEE ICASSP (2003)","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Messer, K., Kittler, J., Sadeghi, M., Hamouz, M., Kostyn, A., Marcel, S., Bengio, S., Cardinaux, F., Sanderson, C., Poh, N., Rodriguez, Y., Czyz, J., et al.: Face authentication test on the BANCA database. In: Proceedings ICPR (2004)","DOI":"10.1109\/ICPR.2004.1333826"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Motlicek, P., Burget, L., Cernocky, J.: Non-parametric speaker turn segmentation of meeting data. In: Proceedings Eurospeech (2005)","DOI":"10.21437\/Interspeech.2005-190"},{"issue":"12","key":"3_CR17","doi-asserted-by":"crossref","first-page":"1424","DOI":"10.1109\/34.895976","volume":"22","author":"M. Pantic","year":"2000","unstructured":"Pantic, M., Rothkrantz, L.J.M.: Automatic analysis of facial expressions: The state of the art. IEEE TPAMI\u00a022(12), 1424\u20131445 (2000)","journal-title":"IEEE TPAMI"},{"key":"3_CR18","unstructured":"Poppe, R., Heylen, D., Nijholt, A., Poel, M.: Towards real-time body pose estimation for presenters in meeting environments. In: Proceedings WSCG (2005)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Potucek, I., Sumec, S., Spanel, M.: Participant activity detection by hands and face movement tracking in the meeting room. In: Proceedings CGI (2004)","DOI":"10.1109\/CGI.2004.1309279"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Rienks, R., Poppe, R., Heylen, D.: Differences in head orientation for speakers and listeners: Experiments in a virtual environment. Int. Journ. HCS (to appear)","DOI":"10.1145\/1658349.1658351"},{"key":"3_CR21","unstructured":"Schwarz, P., Mat\u011bjka, P., \u010cernock\u00fd, J.: Hierarchical structures of neural networks for phoneme recognition. In: IEEE ICASSP (accepted, 2006)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Smith, K., Ba, S., Odobez, J., Gatica-Perez, D.: Evaluating multi-object tracking. In: Workshop on Empirical Evaluation Methods in Computer Vision (2005)","DOI":"10.1109\/CVPR.2005.453"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Smith, K., Ba, S., Odobez, J.M., Gatica-Perez, D.: Multi-person wander-visual-focus-of-attention tracking. Technical Report RR-05-80, IDIAP (2005)","DOI":"10.1145\/1180995.1181048"},{"key":"3_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_8","volume-title":"Machine Learning for Multimodal Interaction","author":"K. Smith","year":"2006","unstructured":"Smith, K., Schreiber, S., Beran, V., Pot\u00facek, I., Gatica-Perez, D.: A comparitive study of head tracking methods. In: Renals, S., Bengio, S., Fiscus, J.G. (eds.) MLMI 2006. LNCS, vol.\u00a04299. Springer, Heidelberg (2006)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Sz\u00f6ke, I., Schwarz, P., Mat\u011bjka, P., Burget, L., Karafi\u00e1t, M., Fap\u0161o, M., \u010cernock\u00fd, J.: Comparison of keyword spotting approaches for informal continuous speech. In: Proceedings Eurospeech (2005)","DOI":"10.1007\/11551874_39"},{"key":"3_CR26","unstructured":"Torch, http:\/\/www.idiap.ch\/~marcel\/en\/torch3\/introduction.php"},{"key":"3_CR27","unstructured":"NIST US: Spring 2004 (RT04S) and Spring 2005 (RT05S) Rich Transcription Meeting Recognition Evaluation Plan. Available at: http:\/\/www.nist.gov\/"},{"key":"3_CR28","unstructured":"Viola, P., Jones, M.: Robust real-time object detection. International Journal of Computer Vision (2002)"},{"key":"3_CR29","unstructured":"Waibel, A., Steusloff, H., Stiefelhagen, R., CHIL Project\u00a0Consortium: CHIL: Computers in the human interaction loop. In: Proceedings of the NIST ICASSP Meeting Recognition Workshop (2004)"},{"key":"3_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1007\/978-3-540-30568-2_2","volume-title":"Machine Learning for Multimodal Interaction","author":"P. Wellner","year":"2005","unstructured":"Wellner, P., Flynn, M., Guillemot, M.: Browsing recorded meetings with Ferret. In: Bengio, S., Bourlard, H. (eds.) MLMI 2004. LNCS, vol.\u00a03361, pp. 12\u201321. Springer, Heidelberg (2005)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Multimodal Interaction"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11965152_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T13:50:20Z","timestamp":1683726620000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11965152_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540692676","9783540692683"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/11965152_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}