{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T16:56:47Z","timestamp":1772038607365,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,4,7]],"date-time":"2013-04-07T00:00:00Z","timestamp":1365292800000},"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"],"published-print":{"date-parts":[[2013,11]]},"DOI":"10.1007\/s12193-013-0120-5","type":"journal-article","created":{"date-parts":[[2013,4,6]],"date-time":"2013-04-06T17:51:30Z","timestamp":1365270690000},"page":"171-182","source":"Crossref","is-referenced-by-count":32,"title":["The W3C multimodal architecture and interfaces standard"],"prefix":"10.1007","volume":"7","author":[{"given":"Deborah A.","family":"Dahl","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,4,7]]},"reference":[{"key":"120_CR1","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1093\/mind\/LIX.236.433","volume":"59","author":"A Turing","year":"1950","unstructured":"Turing A (1950) Computing machinery and intelligence. Mind 59:433\u2013460","journal-title":"Mind"},{"key":"120_CR2","doi-asserted-by":"crossref","unstructured":"Johnston M, Bangalore S, Vasireddy G, Stent A, Ehlen P, Walker M, Whittaker S, Maloor P (2001) MATCH: an architecture for multimodal dialogue systems. In: Proceedings of the 40th annual meeting on association for computational linguistics. Association for, Computational Linguistics, Philadelphia, pp 376\u2013383","DOI":"10.3115\/1073083.1073146"},{"key":"120_CR3","unstructured":"Bayer S (2005) Building a standards and research community with the galaxy communicator software infrastructure. In: Dahl DA (ed) Practical spoken dialog systems, vol 26. TextSpeech and Language Technology. Kluwer Academic Publishers, Dordrecht, pp 166\u2013196"},{"key":"120_CR4","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1145\/319382.319398","volume":"42","author":"SL Oviatt","year":"1999","unstructured":"Oviatt SL (1999) Ten myths of multimodal interaction. Commun ACM 42:74\u201381","journal-title":"Commun ACM"},{"key":"120_CR5","doi-asserted-by":"crossref","unstructured":"Seneff S, Lau R, Polifroni J (1999) Organization, communication, and control in the Galaxy-II Conversational System. In: Proceedings of Eurospeech 1999, Budapest","DOI":"10.21437\/Eurospeech.1999-298"},{"key":"120_CR6","unstructured":"Barnett J, Bodell M, Dahl DA, Kliche I, Larson J, Porter B, Raggett D, Raman TV, Rodriguez BH, Selvaraj M, Tumuluri R, Wahbe A, Wiechno P, Yudkowsky M (2012) Multimodal Architecture and Interfaces. World Wide Web Consortium. http:\/\/www.w3.org\/TR\/mmi-arch\/ . Accessed November 20 2012"},{"key":"120_CR7","unstructured":"Barnett J, Akolkar R, Auburn RJ, Bodell M, Burnett DC, Carter J, McGlashan S, Lager T, Helbing M, Hosn R, Raman TV, Reifenrath K, Rosenthal Na (2012) State chart XML (SCXML): state machine notation for control abstraction. World Wide Web Consortium. http:\/\/www.w3.org\/TR\/scxml\/ . Accessed November 20 2012"},{"key":"120_CR8","unstructured":"McGlashan S, Burnett DC, Carter J, Danielsen P, Ferrans J, Hunt A, Lucas B, Porter B, Rehor K, Tryphonas S (2004) Voice Extensible Markup Language (VoiceXML 2.0). W3C. http:\/\/www.w3.org\/TR\/voicexml20\/ . Accessed November 9 2012"},{"key":"120_CR9","doi-asserted-by":"crossref","unstructured":"Kopp S, Krenn B, Marsella S, Marshall A, Pelachaud C, Pirker H, Th\u00f3risson KR, Vilhj\u00e1lmsson H (2006) Towards a common framework for multimodal generation: The behavior markup language. In: International conference on intelligent virtual agents, Marina del Rey, California","DOI":"10.1007\/11821830_17"},{"key":"120_CR10","doi-asserted-by":"crossref","unstructured":"Heylen D, Kopp S, Marsella S, Pelachaud C, Vilhjalmsson H (2008) The next step towards a functional markup language. Paper presented at the Proceeding of Intelligent Virtual Agents (IVA 2008), Tokyo","DOI":"10.1007\/978-3-540-85483-8_28"},{"key":"120_CR11","doi-asserted-by":"crossref","unstructured":"Scherer S, Marsella S, Stratou G, Xu Y, Morbini F, Egan A, Rizzo A, Morency L-P (2012) Perception markup language: towards a standardized representation of perceived nonverbal behaviors. In: Nakano Y, Neff M, Paiva A, Walker M (eds) Intelligent virtual agents, vol 7502. Lecture Notes in Computer Science. Springer Berlin Heidelberg, pp 455\u2013463. doi: 10.1007\/978-3-642-33197-8_47","DOI":"10.1007\/978-3-642-33197-8_47"},{"key":"120_CR12","doi-asserted-by":"crossref","unstructured":"Araki M, Tachibana K (2006) Multimodal dialog description language for Rapid system development. In: 7th SIGdial workshop on discourse and dialogue, Sydney","DOI":"10.3115\/1654595.1654616"},{"key":"120_CR13","unstructured":"Rodriguez BH, Wiechno P, Dahl DA, Ashimura K, Tumuluri R (2012) Registration & discovery of multimodal modality components in multimodal systems: use cases and requirements. World Wide Web Consortium. http:\/\/www.w3.org\/TR\/mmi-discovery\/ . Accessed November 26 2012"},{"key":"120_CR14","unstructured":"Johnston M, Baggia P, Burnett D, Carter J, Dahl DA, McCobb G, Raggett D (2009) EMMA: extensible multimodal annotation markup language. W3C. http:\/\/www.w3.org\/TR\/emma\/ . Accessed November 9 2012"},{"key":"120_CR15","unstructured":"Bray T, Jean Paoli J, Sperberg-McQueen CM, Maler E, Yergeau F (2004) Extensible Markup Language (XML) 1.0 (Third Edition). World Wide Web Consortium. http:\/\/www.w3.org\/TR\/2004\/REC-xml-20040204\/ . Accessed November 9 2012"},{"key":"120_CR16","unstructured":"Burnett DC, Walker MR, Hunt A (2004) W3C speech synthesis markup language (SSML). W3C. http:\/\/www.w3.org\/TR\/speech-synthesis\/"},{"key":"120_CR17","unstructured":"Oshry M, Auburn RJ, Baggia P, Bodell M, Burke D, Burnett DC, Candell E, Carter J, McGlashan S, Lee A, Porter B, Rehor K (2007) Voice extensible markup language (VoiceXML) 2.1. http:\/\/www.w3.org\/TR\/voicexml21\/ . Accessed November 9 2012"},{"key":"120_CR18","unstructured":"Popescu A (2012) Geolocation API specification. World Wide Web Consortium. http:\/\/www.w3.org\/TR\/geolocation-API\/ . Accessed November 27 2012"},{"key":"120_CR19","unstructured":"Kostiainen A, Oksanen I, Haza\u00ebl-Massieux D (2012) HTML media capture. World Wide Web Consortium. http:\/\/www.w3.org\/TR\/capture-api\/ . Accessed November 27 2012"},{"key":"120_CR20","unstructured":"Microsoft (2007) Microsoft speech API 5.3 (SAPI). http:\/\/msdn2.microsoft.com\/en-us\/library\/ms723627.aspx"},{"key":"120_CR21","unstructured":"Java Speech API (1998) Sun microsystems. http:\/\/java.sun.com\/products\/java-media\/speech\/"},{"key":"120_CR22","unstructured":"SALT Forum (2002) Speech application language tags (SALT). http:\/\/www.saltforum.org"},{"key":"120_CR23","unstructured":"IBM (2003) X+V 1.1. http:\/\/www-3.ibm.com\/software\/pervasive\/multimodal\/x+v\/11\/spec.htm"},{"key":"120_CR24","unstructured":"Bodell M, Bringert B, Brown R, Burnett DC, Dahl DA, Druta D, Ehlen P, Hemphill C, Johnston M, Pettay O, Sampath S, Schr\u00f6der M, Shires G, Tumuluri R, Young M (2011) HTML speech incubator group final report. World Wide Web Consortium. http:\/\/www.w3.org\/2005\/Incubator\/htmlspeech\/XGR-htmlspeech-20111206\/ . Accessed November 27 2012"},{"key":"120_CR25","unstructured":"Kliche I, Dahl DA, Larson JA, Rodriguez BH, Selvaraj M (2011) Best practices for creating MMI modality components. World Wide Web Consortium. http:\/\/www.w3.org\/TR\/2011\/NOTE-mmi-mcbp-20110301\/ . Accessed November 20 2012"},{"key":"120_CR26","unstructured":"Watt SM, Underhill T, Chee Y-M, Franke K, Froumentin M, Madhvanath S, Maga\u00f1a J-A, Pakosz G, Russell G, Selvaraj M, Seni G, Tremblay C, Yaeger L (2011) Ink markup language (InkML). World Wide Web Consortium. http:\/\/www.w3.org\/TR\/InkML . Accessed November 27 2012"},{"key":"120_CR27","unstructured":"Hickson I (2012) Server-sent Events. World Wide Web Consortium. http:\/\/www.w3.org\/TR\/eventsource\/ . Accessed November 20 2012"},{"key":"120_CR28","unstructured":"Hickson I (2012) The WebSocket API. The World Wide Web Consortium. http:\/\/www.w3.org\/TR\/websockets\/ . Accessed November 20 2012"},{"key":"120_CR29","unstructured":"Hunt A, McGlashan S (2004) W3C speech recognition grammar specification (SRGS). W3C. http:\/\/www.w3.org\/TR\/speech-grammar\/ . Accessed November 9 2012"},{"key":"120_CR30","unstructured":"Van Tichelen L, Burke D (2007) Semantic Interpretation for Speech Recognition. W3C. http:\/\/www.w3.org\/TR\/semantic-interpretation\/ . Accessed November 9 2012"},{"key":"120_CR31","unstructured":"Kliche I, Kharidi N, Wiechno P (2012) MMI interoperability test report. World Wide Web Consortium. http:\/\/www.w3.org\/TR\/2012\/NOTE-mmi-interop-20120124\/ . Accessed November 27 2012"},{"key":"120_CR32","unstructured":"Fette I, Melnikov A (2011) RFC 6455: The WebSocket protocol. Internet engineering task force. http:\/\/tools.ietf.org\/html\/rfc6455 . Accessed November 20 2012"},{"key":"120_CR33","unstructured":"Bergkvist A, Burnett DC, Jennings C, Narayanan A (2012) WebRTC 1.0: real-time communication between browsers. World Wide Web Consortium. http:\/\/www.w3.org\/TR\/webrtc\/ . Accessed November 28 2012"},{"key":"120_CR34","unstructured":"Johnston M, Dahl DA, Kliche I, Baggia P, Burnett DC, Burkhardt F, Ashimura K (2009) Use cases for possible future EMMA features. World Wide Web Consortium. http:\/\/www.w3.org\/TR\/emma-usecases\/"},{"key":"120_CR35","unstructured":"Wiechno P, Kharidi N, Kliche I, Rodriguez BH, Schnelle-Walka D, Dahl DA, Ashimura K (2012) Multimodal architecture and interfaces 1.0 implementation report. World Wide Web Consortium. http:\/\/www.w3.org\/2002\/mmi\/2012\/mmi-arch-ir\/ . Accessed November 27 2012"},{"key":"120_CR36","unstructured":"Openstream I (2013) Solutions. http:\/\/www.openstream.com\/solutions.htm . Accessed March 15 2013"},{"key":"120_CR37","doi-asserted-by":"crossref","unstructured":"Rodriguez BH, Moissianc J-C, Demeure I (2010) Multimodal instantiation of assistance services. In: iiWAS \u201910 proceedings of the 12th international conference on information integration and web-based applications & services Paris, ACM, France, pp 934\u2013937","DOI":"10.1145\/1967486.1967652"},{"key":"120_CR38","doi-asserted-by":"crossref","unstructured":"Pous M, Ceccaroni L (2010) Multimodal interaction in distributed and ubiquitous computing. In: Fifth international conference on internet and web applications and services (ICIW), Barcelona, Spain","DOI":"10.1109\/ICIW.2010.75"}],"container-title":["Journal on Multimodal User Interfaces"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-013-0120-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12193-013-0120-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-013-0120-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T21:33:49Z","timestamp":1688160829000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12193-013-0120-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4,7]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,11]]}},"alternative-id":["120"],"URL":"https:\/\/doi.org\/10.1007\/s12193-013-0120-5","relation":{},"ISSN":["1783-7677","1783-8738"],"issn-type":[{"value":"1783-7677","type":"print"},{"value":"1783-8738","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,4,7]]}}}