{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T02:17:04Z","timestamp":1768011424907,"version":"3.49.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2013,11,22]],"date-time":"2013-11-22T00:00:00Z","timestamp":1385078400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Multimodal User Interfaces"],"DOI":"10.1007\/s12193-013-0130-3","type":"journal-article","created":{"date-parts":[[2013,11,21]],"date-time":"2013-11-21T14:48:28Z","timestamp":1385045308000},"source":"Crossref","is-referenced-by-count":13,"title":["An architecture for fluid real-time conversational agents: integrating incremental output generation and input processing"],"prefix":"10.1007","author":[{"given":"Stefan","family":"Kopp","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herwin","family":"van Welbergen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramin","family":"Yaghoubzadeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hendrik","family":"Buschmeier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,11,22]]},"reference":[{"key":"130_CR1","doi-asserted-by":"crossref","unstructured":"Atterer M, Baumann T, Schlangen D. No sooner said than done? Testing incrementality of semantic interpretations of spontaneous speech. In: Proceedings of INTERSPEECH 2009, Brighton, UK, pp 1855\u20131858","DOI":"10.21437\/Interspeech.2009-539"},{"key":"130_CR2","unstructured":"Baumann T, Schlangen D (2012) Inpro_iSS: A component for just-in-time incremental speech synthesis. In: Proceedings of the ACL System Demonstrations, Jeju Island, Korea, pp 103\u2013108"},{"key":"130_CR3","unstructured":"Buschmeier H, Baumann T, Dosch B, Kopp S, Schlangen D. Combining incremental language generation and incremental speech synthesis for adaptive information presentation. In: Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Seoul, South Korea, pp 295\u2013303"},{"key":"130_CR4","doi-asserted-by":"crossref","unstructured":"Buschmeier H, Kopp S (2011) Towards conversational agents that attend to and adapt to communicative user feedback. In: Proceedings of the 11th International Conference on Intelligent Virtual Agents, Reykjavik, Iceland, pp 169\u2013182","DOI":"10.1007\/978-3-642-23974-8_19"},{"key":"130_CR5","unstructured":"Buss O, Schlangen D (2011) DIUM\u2014an incremental dialogue manager that can produce self-corrections. In: SemDial 2011: Proceedings of the 15th Workshop on the Semantics and Pragmatics of Dialogue, Los Angeles, CA, USA, pp 47\u201354"},{"key":"130_CR6","doi-asserted-by":"crossref","first-page":"29","DOI":"10.7551\/mitpress\/2697.001.0001","volume-title":"Embodied conversational agents","author":"J Cassell","year":"2000","unstructured":"Cassell J, Bickmore T, Campbell L, Vilhj\u00e1lmsson H, Yan H (2000) Human conversation as a systems framework: Designing Embodied Conversational Agents. In: Cassell J, Sullivan J, Prevost S, Churchill E (eds) Embodied conversational agents. The MIT Press, Cambridge, pp 29\u201363"},{"key":"130_CR7","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.jml.2003.08.004","volume":"50","author":"HH Clark","year":"2004","unstructured":"Clark HH, Krych MA (2004) Speaking while monitoring addressees for understanding. J Memory Language 50:62\u201381","journal-title":"J Memory Language"},{"key":"130_CR8","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/s12193-012-0090-z","volume":"6","author":"N Crook","year":"2012","unstructured":"Crook N, Field D, Smith C, Harding S, Pulman S, Cavazza M, Charlton D, Moore R, Boye J (2012) Generating context-sensitive ECA responses to user barge-in interruptions. J Multimodal User Interfaces 6:13\u201325","journal-title":"J Multimodal User Interfaces"},{"key":"130_CR9","unstructured":"de Kok I, Heylen D (2012) Integrating backchannel prediction models into embodied conversational agents. In: Proceedings of the 12th International Conference on Intelligent Virtual Agents, Santa Cruz, CA, USA, pp 268\u2013274"},{"key":"130_CR10","unstructured":"Eyben F, Woellmer M, Schuller B (2010) openSMILE\u2014the Munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th International Conference on Multimedia, Florence, Italy, pp 1459\u20131462"},{"key":"130_CR11","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.tics.2003.10.016","volume":"8","author":"S Garrod","year":"2004","unstructured":"Garrod S, Pickering MJ (2004) Why is conversation so easy? Trends Cognit Sci 8:8\u201311","journal-title":"Trends Cognit Sci"},{"key":"130_CR12","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1016\/j.csl.2010.10.003","volume":"25","author":"A Gravano","year":"2011","unstructured":"Gravano A, Hirschberg J (2011) Turn-taking cues in task-oriented dialogue. Comput Speech Language 25:601\u2013634","journal-title":"Comput Speech Language"},{"key":"130_CR13","volume-title":"Incremental conceptualization for language production","author":"M Guhe","year":"2007","unstructured":"Guhe M (2007) Incremental conceptualization for language production. Lawrence Erlbaum Associates, Mahwah"},{"key":"130_CR14","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1007\/s10339-011-0408-x","volume":"12","author":"P Haazebroek","year":"2011","unstructured":"Haazebroek P, van Dantzig S, Hommel B (2011) A computational model of perception and action for cognitive robotics. Cognit Process 12:355\u2013365","journal-title":"Cognit Process"},{"key":"130_CR15","doi-asserted-by":"crossref","unstructured":"Hartholt A, Traum D, Marsella SC, Shapiro A, Stratou G, Leuski A (2013) All together now. In: Proceedings of the 13th International Conference on Intelligent Virtual Agents, Edinburgh, UK, pp 368\u2013381","DOI":"10.1007\/978-3-642-40415-3_33"},{"key":"130_CR16","doi-asserted-by":"crossref","unstructured":"Hartmann B, Mancini M, Pelachaud C (2002) Formational parameters and adaptive prototype instantiation for MPEG-4 compliant gesture synthesis. In: Computer, Animation, pp 111\u2013119","DOI":"10.1109\/CA.2002.1017516"},{"key":"130_CR17","unstructured":"Hoffman G, Breazeal C (2008) Anticipatory perceptual simulation for human-robot joint practice: Theory and application study. In: Proceedings of the 23rd AAAI Confererence for Artificial Intelligence, Chicago, IL, USA, pp 1357\u20131362"},{"key":"130_CR18","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.neunet.2006.07.003","volume":"20","author":"H Hoffmann","year":"2007","unstructured":"Hoffmann H (2007) Perception through visuomotor anticipation in a mobile robot. Neural Netw 20:22\u201333","journal-title":"Neural Netw"},{"key":"130_CR19","doi-asserted-by":"crossref","first-page":"297","DOI":"10.5087\/dad.2011.111","volume":"2","author":"C Howes","year":"2011","unstructured":"Howes C, Purver M, Healey PGT, Mills G, Gregoromichelaki E (2011) On incrementality in dialogue: evidence from compound contributions. Dialogue Discourse 2:297\u2013311","journal-title":"Dialogue Discourse"},{"key":"130_CR20","unstructured":"Kenny PG, Parsons TD, Pataki C, Pato M, St. George C, Sugar J, Rizzo A (2008) Virtual Justina: A PTSD virtual patient for clinical classroom training. Annu Rev CyberTher Telemed 6:113\u2013118"},{"key":"130_CR21","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/j.specom.2010.02.007","volume":"52","author":"S Kopp","year":"2010","unstructured":"Kopp S (2010) Social resonance and embodied coordination in face-to-face conversation with artificial interlocutors. Speech Commun 52:587\u2013597","journal-title":"Speech Commun"},{"key":"130_CR22","doi-asserted-by":"crossref","unstructured":"Kopp S, Gesellensetter L, Kramer NC, Wachsmuth I (2005) A conversational agent as museum guide - Design and evaluation of a real-world application. In: Proceedings of the 5th International Working Conference on Intelligent Virtual Agents, Kos, Greece, pp 329\u2013343","DOI":"10.1007\/11550617_28"},{"key":"130_CR23","doi-asserted-by":"crossref","unstructured":"Kopp S, Krenn B, Marsella SC, Marshall AN, Pelachaud C, Pirker H, Th\u00f3risson KR, Vilhj\u00e1lmsson HH (2006) Towards a common framework for multimodal generation: the behavior markup language. In: Proceedings of the 6th International Working Conference on Intelligent Virtual Agents, vol 4133, Marina del Rey, CA, USA, pp 205\u2013217","DOI":"10.1007\/11821830_17"},{"key":"130_CR24","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1002\/cav.6","volume":"15","author":"S Kopp","year":"2004","unstructured":"Kopp S, Wachsmuth I (2004) Synthesizing multimodal utterances for conversational agents. Comput Animat Virtual Worlds 15:39\u201352","journal-title":"Comput Animat Virtual Worlds"},{"key":"130_CR25","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1145\/1017494.1017496","volume":"11","author":"O Lemon","year":"2004","unstructured":"Lemon O, Gruenstein A (2004) Multithreaded context for robust conversational interfaces: context-sensitive speech recognition and interpretation of corrective fragments. ACM Trans Comput Human Interact 11:241\u2013267","journal-title":"ACM Trans Comput Human Interact"},{"key":"130_CR26","unstructured":"Lison P, Kruijff G-J (2008) Salience-driven contextual priming of speech recognition for human-robot interaction. In: Proceedings of the 18th European Conference on Artificial Intelligence, Patras, Greece, pp 636\u2013640"},{"key":"130_CR27","doi-asserted-by":"crossref","unstructured":"Neiberg D, Truong KP (2011) Online detection of vocal listener responses with maximum latency constraints. In: International Conference on Acoustics, Speech, and, Signal Processing, pp 5836\u20132539","DOI":"10.1109\/ICASSP.2011.5947688"},{"key":"130_CR28","doi-asserted-by":"crossref","unstructured":"Nijholt A, Reidsma D, van Welbergen H, op den Akker H , Ruttkay ZM (2008) Mutually coordinated anticipatory multimodal interaction. In: Esposito A, Bourbakis NG, Avouris N, Hatzilygeroudis I (eds) Verbal and nonverbal features of human\u2013human and human\u2013machine interaction, Springer, Berlin, pp 70\u201389","DOI":"10.1007\/978-3-540-70872-8_6"},{"key":"130_CR29","unstructured":"Reidsma D, Dehling E, van Welbergen H, Zwiers J, Nijholt A (2011) Leading and following with a virtual trainer. In: Proceedings of the 4th International Workshop on Whole Body Interaction in Games and Entertainment, Lisbon, Portugal"},{"key":"130_CR30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1461999.1462005","volume":"6","author":"D Reidsma","year":"2008","unstructured":"Reidsma D, Nijholt A, Bos P (2008) Temporal interaction between an artificial orchestra conductor and human musicians. Comput Entertain 6:1\u201322","journal-title":"Comput Entertain"},{"key":"130_CR31","doi-asserted-by":"crossref","unstructured":"Reidsma D, van Welbergen H, Poppe R, Bos P, Nijholt A (2006) Towards bi-directional dancing interaction. In: Proceedings of the 5th International Conference on Entertainment Computing, Cambridge, UK, pp 1\u201312","DOI":"10.1007\/11872320_1"},{"key":"130_CR32","doi-asserted-by":"crossref","unstructured":"Ribeiro T, Vala M, Paiva A (2012) Thalamus: closing the mind-body loop in interactive embodied characters. In: Proceedings of the 12th International Conference on Intelligent Virtual Agents, Santa Cruz, CA, USA, pp 189\u2013195","DOI":"10.1007\/978-3-642-33197-8_19"},{"key":"130_CR33","doi-asserted-by":"crossref","first-page":"696","DOI":"10.2307\/412243","volume":"50","author":"H Sacks","year":"1974","unstructured":"Sacks H, Schegloff EA, Jefferson G (1974) A simplest systematics for the organization of turn-taking for conversation. Language 50:696\u2013735","journal-title":"Language"},{"key":"130_CR34","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1007\/s12559-010-9082-z","volume":"3","author":"A Sadeghipour","year":"2011","unstructured":"Sadeghipour A, Kopp S (2011) Embodied gesture processing: Motor-based perception-action integration in social artificial agents. Cognitive Computation 3:419\u2013435","journal-title":"Cognitive Computation"},{"key":"130_CR35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/S0047404500001019","volume":"29","author":"E Schegloff","year":"2000","unstructured":"Schegloff E (2000) Overlapping talk and the organization of turn-taking for conversation. Language Soc 29:1\u201363","journal-title":"Language Soc"},{"key":"130_CR36","doi-asserted-by":"crossref","unstructured":"Scherer S, Marsella S, Stratou G, Xu Y, Morbini F, Egan A, Rizzo AS, Morency L-P (2012) Perception markup language: towards a standardized representation of perceived nonverbal behaviors. In: Proceedings of the 12th International Conference on Intelligent Virtual Agents, Santa Cruz, CA, USA, pp 455\u2013463","DOI":"10.1007\/978-3-642-33197-8_47"},{"key":"130_CR37","unstructured":"Schlangen D, Baumann T, Buschmeier H, Bu\u00df O, Kopp S, Skantze G, Yaghoubzadeh R (2010) Middleware for incremental processing in conversational agents. In: Proceedings of the 11th Annual SIGdial Meeting on Discourse and, Dialogue, pp 51\u201354"},{"key":"130_CR38","doi-asserted-by":"crossref","first-page":"83","DOI":"10.5087\/dad.2011.105","volume":"2","author":"D Schlangen","year":"2011","unstructured":"Schlangen D, Skantze G (2011) A general, abstract model of incremental dialogue processing. Dialogue Discourse 2:83\u2013111","journal-title":"Dialogue Discourse"},{"key":"130_CR39","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1162\/coli.08-011-R2-07-021","volume":"35","author":"W Schuler","year":"2009","unstructured":"Schuler W, Wu S, Schwartz L (2009) A framework for fast incremental interpretation during speech decoding. Comput Linguist 35:313\u2013343","journal-title":"Comput Linguist"},{"key":"130_CR40","doi-asserted-by":"crossref","unstructured":"Seneff S, Wang C, Hetherington L, Chung G (2004) A dynamic vocabulary spoken dialogue interface. In: Proceedings of INTERSPEECH 2004, Jeju Island, Korea, pp 321\u2013324","DOI":"10.21437\/Interspeech.2004-148"},{"key":"130_CR41","unstructured":"Skantze G, Hjalmarsson A (2010) Towards incremental speech generation in dialogue systems. In: Proceedings of the 11th Annual SIGdial Meeting on Discourse and, Dialogue, pp 1\u20138"},{"key":"130_CR42","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1046\/j.0824-7935.2003.00221.x","volume":"19","author":"M Stone","year":"2003","unstructured":"Stone M, Doran C, Webber B, Bleam T, Palmer M (2003) Microplanning with communicative intentions: the SPUD system. Computat Intell 19:311\u2013381","journal-title":"Computat Intell"},{"key":"130_CR43","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1111\/j.1468-2958.1984.tb00043.x","volume":"11","author":"RL Street","year":"1984","unstructured":"Street RL (1984) Speech convergence and speech evaluation in fact-finding interviews. Human Commun Res 11:139\u2013169","journal-title":"Human Commun Res"},{"key":"130_CR44","doi-asserted-by":"crossref","first-page":"1632","DOI":"10.1126\/science.7777863","volume":"268","author":"MK Tanenhaus","year":"1995","unstructured":"Tanenhaus MK, Spivey-Knowlton MJ, Eberhard KM, Sedivy JC (1995) Integration of visual and linguistic information in spoken language comprehension. Science 268:1632\u20131634","journal-title":"Science"},{"key":"130_CR45","unstructured":"Th\u00f3risson KR (1996) Communicative Humanoids. A computational model of psychosocial dialogue skills. PhD thesis, Massachusetts Institute of Technology, Cambridge, MA, USA"},{"key":"130_CR46","doi-asserted-by":"crossref","unstructured":"Traum D, DeVault D, Lee J, Wang Z, Marsella S (2012) Incremental dialogue understanding and feedback for multiparty, multimodal conversation. In: Proceedings of the 12th International Conference on Intelligent Virtual Agents, Santa Cruz, CA, USA, pp 275\u2013288","DOI":"10.1007\/978-3-642-33197-8_29"},{"key":"130_CR47","doi-asserted-by":"crossref","unstructured":"van Welbergen H, Reidsma D, Kopp S (2012) An incremental multimodal realizer for behavior co-articulation and coordination. In: Proceedings of the 12th International Conference on Intelligent Virtual Agents, Santa Cruz, CA, USA, pp 175\u2013188","DOI":"10.1007\/978-3-642-33197-8_18"},{"key":"130_CR48","doi-asserted-by":"crossref","unstructured":"Vilhj\u00e1lmsson HH, Cantelmo N, Cassell J, Chafai NE, Kipp M, Kopp S, Mancini M, Marsella SC, Marshall AN, Pelachaud C, Ruttkay ZM, Th\u00f3risson KR, van Welbergen H, van der Werf RJ (2007) The behavior markup language: recent developments and challenges. In: Proceedings of the 7th International Conference on Intelligent Virtual Agents, Paris, France, pp 99\u2013120","DOI":"10.1007\/978-3-540-74997-4_10"},{"key":"130_CR49","doi-asserted-by":"crossref","first-page":"1755","DOI":"10.1037\/a0016798","volume":"35","author":"A Wykowska","year":"2009","unstructured":"Wykowska A, Schub\u00f6 A, Hommel B (2009) How you move is what you see: action planning biases selection in visual search. J Exp Psychol Human Percept Perform 35:1755\u20131769","journal-title":"J Exp Psychol Human Percept Perform"}],"container-title":["Journal on Multimodal User Interfaces"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-013-0130-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12193-013-0130-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-013-0130-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,16]],"date-time":"2022-03-16T23:27:17Z","timestamp":1647473237000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12193-013-0130-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11,22]]},"references-count":49,"alternative-id":["130"],"URL":"https:\/\/doi.org\/10.1007\/s12193-013-0130-3","relation":{},"ISSN":["1783-7677","1783-8738"],"issn-type":[{"value":"1783-7677","type":"print"},{"value":"1783-8738","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,11,22]]}}}