{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:34:24Z","timestamp":1742916864595,"version":"3.40.3"},"publisher-location":"Tokyo","reference-count":45,"publisher":"Springer Japan","isbn-type":[{"type":"print","value":"9784431558651"},{"type":"electronic","value":"9784431558675"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-4-431-55867-5_9","type":"book-chapter","created":{"date-parts":[[2016,1,6]],"date-time":"2016-01-06T06:04:55Z","timestamp":1452060295000},"page":"239-270","source":"Crossref","is-referenced-by-count":3,"title":["Smart Posterboard: Multi-modal Sensing and Analysis of Poster Conversations"],"prefix":"10.1007","author":[{"given":"Tatsuya","family":"Kawahara","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,1,7]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"S. Renals, T. Hain, H. Bourlard, Recognition and understanding of meetings: The AMI and AMIDA projects. Proceedings of IEEE Workshop Automatic Speech Recognition & Understanding (2007)","DOI":"10.1109\/ASRU.2007.4430116"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"K. Ohtsuka, Conversation scene analysis. Signal Process. Magaz. 28(4), 127\u2013131 (2011)","DOI":"10.1109\/MSP.2011.941100"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"T. Kawahara, Multi-modal sensing and analysis of poster conversations toward smart posterboard. In Proceedings of SIGdial Meeting Discourse and Dialogue, pp. 1\u20139 (keynote speech) (2012)","DOI":"10.1109\/APSIPA.2013.6694345"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"T. Kawahara, Smart posterboard: Multi-modal sensing and analysis of poster conversations. In Proceedings of APSIPA ASC, page (plenary overview talk) (2013)","DOI":"10.1109\/APSIPA.2013.6694345"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"T. Kawahara, H.Setoguchi, K. Takanashi, K.Ishizuka, S. Araki, Multi-modal recording, analysis and indexing of poster sessions. Proceedings of INTERSPEECH, pp. 1622\u20131625 (2008)","DOI":"10.21437\/Interspeech.2008-451"},{"key":"9_CR6","unstructured":"K. Maekawa, Corpus of spontaneous Japanese: its design and evaluation. Proceedings of ISCA and IEEE Workshop on Spontaneous Speech Processing and Recognition, pp. 7\u201312 (2003)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"H. Yoshimoto, Y. Nakamura, Cubistic representation for real-time 3D shape and pose estimation of unknown rigid object. Proceedings ICCV, Workshop, pp. 522\u2013529 (2013)","DOI":"10.1109\/ICCVW.2013.74"},{"issue":"4","key":"9_CR8","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1109\/TASL.2008.2011517","volume":"17","author":"Yu Takahashi","year":"2009","unstructured":"Y. Takahashi, T. Takatani, K. Osako, H. Saruwatari, K. Shikano, Blind spatial subtraction array for speech enhancement in noisy environment. IEEE Trans. Audio, Speech Language Process. 17(4), 650\u2013664 (2009)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"T.\u00a0Ohsuga, M.\u00a0Nishida, Y.\u00a0Horiuchi, A.\u00a0Ichikawa, Investigation of the relationship between turn-taking and prosodic features in spontaneous dialogue. Proceedings INTERSPEECH, pp. 33\u201336 (2005)","DOI":"10.21437\/Interspeech.2005-32"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"C.T. Ishi, H.\u00a0Ishiguro, N.\u00a0Hagita, Analysis of prosodic and linguistic cues of phrase finals for turn-taking and dialog acts. Proceedings of INTERSPEECH, pp. 2006\u20132009 (2006)","DOI":"10.21437\/Interspeech.2006-549"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"N.G. Ward, Y.A. Bayyari, A case study in the identification of prosodic cues to turn-taking: back-channeling in Arabic. Proceedings of INTERSPEECH, pp. 2018\u20132021 (2006)","DOI":"10.21437\/Interspeech.2006-552"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"B.\u00a0Xiao, V.\u00a0Rozgic, A.\u00a0Katsamanis, B.R. Baucom, P.G. Georgiou, S.\u00a0Narayanan, Acoustic and visual cues of turn-taking dynamics in dyadic interactions. Proceedings of INTERSPEECH, pp. 2441\u20132444 (2011)","DOI":"10.21437\/Interspeech.2011-635"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"R.\u00a0Sato, R.\u00a0Higashinaka, M.\u00a0Tamoto, M.\u00a0Nakano, K.\u00a0Aikawa, Learning decision trees to determine turn-taking by spoken dialogue systems. Proceedings of ICSLP, pp. 861\u2013864 (2002)","DOI":"10.21437\/ICSLP.2002-293"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"D.\u00a0Schlangen, From reaction to prediction: experiments with computational models of turn-taking. Proceedings INTERSPEECH, pp. 2010\u20132013 (2006)","DOI":"10.21437\/Interspeech.2006-550"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"A. Raux, M. Eskenazi, A finite-state turn-taking model for spoken dialog systems. Proceedings of HLT\/NAACL (2009)","DOI":"10.3115\/1620754.1620846"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"N.G. Ward, O.\u00a0Fuentes, A.\u00a0Vega, Dialog prediction for a general model of turn-taking. Proceedings of INTERSPEECH, pp. 2662\u20132665 (2010)","DOI":"10.21437\/Interspeech.2010-706"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"S.\u00a0Benus, Are we \u2019in sync\u2019: turn-taking in collaborative dialogues. Proceedings of INTERSPEECH, pp. 2167\u20132170 (2009)","DOI":"10.21437\/Interspeech.2009-618"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"N.\u00a0Campbell, S.\u00a0Scherer, Comparing measures of synchrony and alignment in dialogue speech timing with respect to turn-taking activity. Proceedings of INTERSPEECH, pp. 2546\u20132549 (2010)","DOI":"10.21437\/Interspeech.2010-689"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"D. Bohus, E. Horvitz, Models for multiparty engagement in open-world dialog. Proceedings of SIGdial (2009)","DOI":"10.3115\/1708376.1708409"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"S.\u00a0Fujie, Y.\u00a0Matsuyama, H.\u00a0Taniyama, T.\u00a0Kobayashi, Conversation robot participating in and activating a group communication. Proceedings of INTERSPEECH, pp. 264\u2013267 (2009)","DOI":"10.21437\/Interspeech.2009-91"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"K.\u00a0Laskowski, J.\u00a0Edlund, M.\u00a0Heldner, A single-port non-parametric model of turn-taking in multi-party conversation. Proceedings of ICASSP, pp. 5600\u20135603 (2011)","DOI":"10.1109\/ICASSP.2011.5947629"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"K. Jokinen, K. Harada, M. Nishida, S. Yamamoto, Turn-alignment using eye-gaze and speech in conversational interaction. Proceedings of InterSpeech, pp. 2018\u20132021 (2011)","DOI":"10.21437\/Interspeech.2010-571"},{"key":"9_CR23","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/0001-6918(67)90005-4","volume":"26","author":"A Kendon","year":"1967","unstructured":"A. Kendon, Some functions of gaze direction in social interaction. Acta Psychol. 26, 22\u201363 (1967)","journal-title":"Acta Psychol."},{"issue":"5","key":"9_CR24","first-page":"1557","volume":"14","author":"SE Tranter","year":"2006","unstructured":"S.E. Tranter, D.A. Reynolds, An overview of automatic speaker diarization systems. IEEE Trans. ASLP 14(5), 1557\u20131565 (2006)","journal-title":"IEEE Trans. ASLP"},{"issue":"2","key":"9_CR25","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1109\/TASL.2011.2158419","volume":"20","author":"G. Friedland","year":"2012","unstructured":"G.\u00a0Friedland, A.\u00a0Janin, D.\u00a0Imseng, X.\u00a0Anguera Miro, L.\u00a0Gottlieb, M.\u00a0Huijbregts, M.T. Knox, O.\u00a0Vinyals, The ICSI RT-09 speaker diarization system. IEEE Trans. ASLP 20(2), 371\u2013381 (2012)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"9_CR26","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1109\/TAP.1986.1143830","volume":"34","author":"R Schmidt","year":"1986","unstructured":"R. Schmidt, Multiple emitter location and signal parameter estimation. IEEE Trans. Antennas Propag. 34(3), 276\u2013280 (1986)","journal-title":"IEEE Trans. Antennas Propag."},{"issue":"8","key":"9_CR27","doi-asserted-by":"crossref","first-page":"2158","DOI":"10.1093\/ietfec\/e89-a.8.2158","volume":"E89-A","author":"K. YAMAMOTO","year":"2006","unstructured":"K.\u00a0Yamamoto, F.\u00a0Asano, T.\u00a0Yamada, N.\u00a0Kitawaki, Detection of overlapping speech in meetings using support vector machines and support vector regression. IEICE Trans. E89-A(8), 2158\u20132165 (2006)","journal-title":"IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"},{"key":"9_CR28","first-page":"741","volume":"2","author":"H Misra","year":"2003","unstructured":"H. Misra, H. Bourlard, V. Tyagi, New entropy based combination rules in hmm\/ann multi-stream asr. Proc. ICASSP 2, 741\u2013744 (2003)","journal-title":"Proc. ICASSP"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"S.\u00a0Araki, M.\u00a0Fujimoto, K.\u00a0Ishizuka, H.\u00a0Sawada, S.\u00a0Makino, A DOA based speaker diarization system for real meetings. Prooceedings of HSCMA, pp. 29\u201332 (2008)","DOI":"10.1109\/HSCMA.2008.4538680"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Y. Wakabayashi, K. Inoue, H. Yoshimoto, T. Kawahara, Speaker diarization based on audio-visual integration for smart posterboard. Proceedings of APSIPA ASC (2014)","DOI":"10.1109\/APSIPA.2014.7041584"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"J.G. Fiscus, J.\u00a0Ajot, M.\u00a0Michel, J.S. Garofolo, The Rich Transcription 2006 Spring Meeting Recognition Evaluation (Springer, 2006)","DOI":"10.1007\/11965152_28"},{"issue":"3\u20134","key":"9_CR32","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1177\/002383099804100404","volume":"41","author":"H Koiso","year":"1998","unstructured":"H. Koiso, Y. Horiuchi, S. Tutiya, A. Ichikawa, Y. Den, An analysis of turn-taking and backchannels based on prosodic and syntactic features in Japanese map task dialogs. Language & Speech 41(3\u20134), 295\u2013321 (1998)","journal-title":"Language & Speech"},{"issue":"8","key":"9_CR33","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1016\/S0378-2166(99)00109-5","volume":"32","author":"N Ward","year":"2000","unstructured":"N. Ward, W. Tsukahara, Prosodic features which cue back-channel responses in English and Japanese. J. Pragmatics 32(8), 1177\u20131207 (2000)","journal-title":"J. Pragmatics"},{"issue":"3","key":"9_CR34","first-page":"220","volume":"20","author":"N Kitaoka","year":"2005","unstructured":"N. Kitaoka, M. Takeuchi, R. Nishimura, S. Nakagawa, Response timing detection using prosodic and linguistic information for human-friendly spoken dialog systems. J. Japn. Soc. Artific. Intell. 20(3), 220\u2013228 (2005)","journal-title":"J. Japn. Soc. Artific. Intell."},{"key":"9_CR35","unstructured":"D. Ozkan, L.-P. Morency, Modeling wisdom of crowds using latent mixture of discriminative experts. Proceedings of ACL\/HLT (2011)"},{"key":"9_CR36","unstructured":"L.S.Kennedy, D.P.W. Ellis, Laughter detection in meetings. NIST Meeting Recognition Workshop (2004)"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"K.P. Truong, D.A. van Leeuwen, Automatic detection of laughter. Proceedings InterSpeech, pp. 485\u2013488 (2005)","DOI":"10.21437\/Interspeech.2005-322"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"K.Laskowski, Contrasting emotion-bearing laughter types in multiparticipant vocal activity detection for meetings. Proceedings of IEEE-ICASSP, pp. 4765\u20134768 (2009)","DOI":"10.1109\/ICASSP.2009.4960696"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"N. Ward, Pragmatic functions of prosodic features in non-lexical utterances. Speech Prosody, pp. 325\u2013328 (2004)","DOI":"10.21437\/SpeechProsody.2004-76"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"F. Yang, G. Tur, E. Shriberg, Exploiting dialog act tagging and prosodic information for action item identification. Proceedings of IEEE-ICASSP, pp. 4941\u20134944 (2008)","DOI":"10.1109\/ICASSP.2008.4518766"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"A. Gravano, S. Benus, J. Hirschberg, S. Mitchell, I. Vovsha, Classification of discourse functions of affirmative words in spoken dialogue. Proceedings of InterSpeech, pp. 1613\u20131616 (2007)","DOI":"10.21437\/Interspeech.2007-450"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"K. Sumi, T. Kawahara, J. Ogata, M. Goto, Acoustic event detection for spotting hot spots in podcasts. Proceedings of INTERSPEECH, pp. 1143\u20131146 (2009)","DOI":"10.21437\/Interspeech.2009-333"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"M. Goto, K. Itou, S. Hayamizu, A real-time filled pause detection system for spontaneous speech recognition research. Proceedings of EuroSpeech, pp. 227\u2013230 (1999)","DOI":"10.21437\/Eurospeech.1999-60"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"T. Kawahara, Z.Q. Chang, K. Takanashi, Analysis on prosodic features of Japanese reactive tokens in poster conversations. Proceedings Int\u2019l Conference Speech Prosody (2010)","DOI":"10.21437\/SpeechProsody.2010-107"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"S. Strombergsson, J. Edlund, D. House, Prosodic measurements and question types in the spontal corpus of Swedish dialogues. Proceedings of InterSpeech (2012)","DOI":"10.21437\/Interspeech.2012-189"}],"container-title":["Human-Harmonized Information Technology, Volume 1"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-4-431-55867-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T16:56:10Z","timestamp":1718297770000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-4-431-55867-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9784431558651","9784431558675"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-4-431-55867-5_9","relation":{},"subject":[],"published":{"date-parts":[[2016]]}}}