{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T01:04:24Z","timestamp":1752282264580},"publisher-location":"Berlin, Heidelberg","reference-count":40,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642181832"},{"type":"electronic","value":"9783642181849"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"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":[[2011]]},"DOI":"10.1007\/978-3-642-18184-9_6","type":"book-chapter","created":{"date-parts":[[2011,1,18]],"date-time":"2011-01-18T04:57:55Z","timestamp":1295326675000},"page":"55-71","source":"Crossref","is-referenced-by-count":6,"title":["Audio-Visual Prosody: Perception, Detection, and Synthesis of Prominence"],"prefix":"10.1007","author":[{"given":"Samer","family":"Al Moubayed","sequence":"first","affiliation":[]},{"given":"Jonas","family":"Beskow","sequence":"additional","affiliation":[]},{"given":"Bj\u00f6rn","family":"Granstr\u00f6m","sequence":"additional","affiliation":[]},{"given":"David","family":"House","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"McGurk, H., MacDonald, J.: Hearing lips and seeing voices, vol.\u00a0264, pp. 746\u2013748 (1976)","DOI":"10.1038\/264746a0"},{"issue":"1273","key":"6_CR2","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1098\/rstb.1992.0009","volume":"335","author":"Q. Summerfield","year":"1992","unstructured":"Summerfield, Q.: Lipreading and audio-visual speech perception. Philosophical Transactions: Biological Sciences\u00a0335(1273), 71\u201378 (1992)","journal-title":"Philosophical Transactions: Biological Sciences"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Cave, C., Gua\u00eftella, I., Bertrand, R., Santi, S., Harlay, F., Espesser, R.: About the relationship between eyebrow movements and Fo variations. In: Proc. of the Fourth International Conference on Spoken Language, vol.\u00a04 (1996)","DOI":"10.21437\/ICSLP.1996-551"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Munhall, K., Jones, J., Callan, D., Kuratate, T., Vatikiotis-Bateson, E.: Head Movement Improves Auditory Speech Perception Psychological Science, vol.\u00a015(2), pp. 133\u2013137 (2004)","DOI":"10.1111\/j.0963-7214.2004.01502010.x"},{"issue":"3","key":"6_CR5","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.cognition.2005.09.002","volume":"100","author":"C. Davis","year":"2006","unstructured":"Davis, C., Kim, J.: Audio-visual speech perception off the top of the head. Cognition\u00a0100(3), 21\u201331 (2006)","journal-title":"Cognition"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Cvejic, E., Kim, J., Davis, C.: Prosody off the top of the head: Prosodic contrasts can be discriminated by head motion. Speech Communication (2010)","DOI":"10.1016\/j.specom.2010.02.006"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Terken, J., Hermes, D.: The perception of prosodic prominence, in Prosody: Theory and Experiment. Studies Presented to G\u00f6sta Bruce. pp. 89\u2013127 (2000)","DOI":"10.1007\/978-94-015-9413-4_5"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Streefkerk, B., Pols, L., Bosch, L.: Acoustical features as predictors for prominence in read aloud Dutch sentences used in ANN\u2019s. In: Sixth European Conference on Speech Communication and Technology, Citeseer (1999)","DOI":"10.21437\/Eurospeech.1999-142"},{"issue":"3-4","key":"6_CR9","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/S0095-4470(19)30327-4","volume":"19","author":"G. Fant","year":"1991","unstructured":"Fant, G., Kruckenberg, A., Nord, L.: Durational correlates of stress in Swedish, French, and English. Journal of phonetics\u00a019(3-4), 351\u2013365 (1991)","journal-title":"Journal of phonetics"},{"key":"6_CR10","unstructured":"Bruce, G.: Swedish word accents in sentence perspective. LiberL\u00e4romedel\/Gleerup (1977)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Gussenhoven, C., Bruce, G.: Word prosody and intonation.Empirical Approaches to Language Typology, 233\u2013272 (1999)","DOI":"10.1515\/9783110197082.1.233"},{"issue":"3","key":"6_CR12","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1006\/jpho.2001.0143","volume":"29","author":"M. Heldner","year":"2001","unstructured":"Heldner, M., Strangert, E.: Temporal effects of focus in Swedish. Journal of Phonetics\u00a029(3), 329\u2013361 (2001)","journal-title":"Journal of Phonetics"},{"issue":"3","key":"6_CR13","first-page":"2000","volume":"2","author":"G. Fant","year":"2000","unstructured":"Fant, G., Kruckenberg, A., Liljencrants, J., Herteg\u00e5rd, S.: Acoustic phonetic studies of prominence in Swedish. KTH TMH-QPSR\u00a02(3), 2000 (2000)","journal-title":"KTH TMH-QPSR"},{"key":"6_CR14","unstructured":"Fant, G., Kruckenberg, A.: Notes on stress and word accent in Swedish. In: Proceedings of the International Symposium on Prosody, Yokohama, September 18, pp. 2\u20133 (1994)"},{"issue":"3-4","key":"6_CR15","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1016\/j.specom.2005.02.017","volume":"46","author":"B. Granstr\u00f6m","year":"2005","unstructured":"Granstr\u00f6m, B., House, D.: Audiovisual representation of prosody in expressive speech communication. Speech Communication\u00a046(3-4), 473\u2013484 (2005)","journal-title":"Speech Communication"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Beskow, J., Granstr\u00f6m, B., House, D.: Visual correlates to prominence in several expressive modes. In: Proc of the Ninth International Conference on Spoken Language Processing (2006)","DOI":"10.21437\/Interspeech.2006-375"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"House, D., Beskow, J., Granstr\u00f6m, B.: Timing and interaction of visual cues for prominence in audiovisual speech perception. In: Proc. of the Seventh European Conference on Speech Communication and Technology (2001)","DOI":"10.21437\/Eurospeech.2001-61"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Swerts, M., Krahmer, E.: The importance of different facial areas for signalling visual prominence. In: Proc. of the Ninth International Conference on Spoken Language Processing (2006)","DOI":"10.21437\/Interspeech.2006-377"},{"issue":"3","key":"6_CR19","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1016\/j.jml.2007.06.005","volume":"57","author":"E. Krahmer","year":"2007","unstructured":"Krahmer, E., Swerts, M.: The effects of visual beats on prosodic prominence: Acoustic analyses, auditory perception and visual perception. Journal of Memory and Language\u00a057(3), 396\u2013414 (2007)","journal-title":"Journal of Memory and Language"},{"issue":"2-3","key":"6_CR20","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1177\/0023830909103166","volume":"52","author":"M. Dohen","year":"2009","unstructured":"Dohen, M., L\u0153venbruck, H.: Interaction of audition and vision for the perception of prosodic contrastive focus. Language and Speech\u00a052(2-3), 177 (2009)","journal-title":"Language and Speech"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Dohen, M., Lcevenbruck, H., Hill, H.: Recognizing Prosody from the Lips: Is It Possible to Extract Prosodic Focus. Visual Speech Recognition: Lip Segmentation and Mapping, 416 (2009)","DOI":"10.4018\/978-1-60566-186-5.ch014"},{"issue":"2","key":"6_CR22","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1109\/TASL.2006.881703","volume":"15","author":"D. Wang","year":"2007","unstructured":"Wang, D., Narayanan, S.: An acoustic measure for word prominence in spontaneous speech. IEEE Transactions on Audio, Speech, and Language Processing\u00a015(2), 690\u2013701 (2007)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"6_CR23","unstructured":"Grice, M., Savino, M.: Can pitch accent type convey information status in yes-no questions. In: Proc. of the Workshop Sponsored by the Association for Computational Linguistics, pp. 29\u201338 (1997)"},{"key":"6_CR24","unstructured":"Al Moubayed, S., Beskow, J.: Effects of visual prominence cues on speech intelligibility. In: Proceedings of the International Conference on Auditory Visual Speech Processing AVSP 2009, vol.\u00a015, p. 16 (2009)"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Tamburini, F.: Prosodic prominence detection in speech. In: Proceedings of the Seventh International Symposium on Signal Processing and Its Applications, vol.\u00a01 (2003)","DOI":"10.1109\/ISSPA.2003.1224721"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Agelfors, E., Beskow, J., Dahlquist, M., Granstr\u00f6m, B., Lundeberg, M., Spens, K.-E., \u00d6hman, T.: Synthetic faces as a lipreading support. In: Proceedings of ICSLP 1998 (1998)","DOI":"10.21437\/ICSLP.1998-785"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Salvi, G., Beskow, J., Al Moubayed, S., Granstr\u00f6m, B.: Synface - speech-driven facial animation for virtual speech-reading support. Journal on Audio, Speech and Music Processing (2009)","DOI":"10.1155\/2009\/191940"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Beskow, J.: Rule-based visual speech synthesis. In: Proc. of the Fourth European Conference on Speech Communication and Technology (1995)","DOI":"10.21437\/Eurospeech.1995-81"},{"key":"6_CR29","unstructured":"Sj\u00f6lander, K.: An HMM-based system for automatic segmentation and alignment of speech. In: Proceedings of Fonetik, pp. 93\u201396 (2003)"},{"issue":"4","key":"6_CR30","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1023\/B:IJST.0000037076.86366.8d","volume":"7","author":"J. Beskow","year":"2004","unstructured":"Beskow, J.: Trainable articulatory control models for visual speech synthesis. International Journal of Speech Technology\u00a07(4), 335\u2013349 (2004)","journal-title":"International Journal of Speech Technology"},{"issue":"5234","key":"6_CR31","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1126\/science.270.5234.303","volume":"270","author":"R. Shannon","year":"1995","unstructured":"Shannon, R., Zeng, F., Kamath, V., Wygonski, J., Ekelid, M.: Speech recognition with primarily temporal cues. Science\u00a0270(5234), 303 (1995)","journal-title":"Science"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Al Moubayed, S., Beskow, J., Oster, A.-M., Salvi, G., Granstr\u00f6m, B., van Son, N., Ormel, E.: Virtual speech reading support for hard of hearing in a domestic multi-media setting. In: Proceedings of Interspeech 2009 (2009)","DOI":"10.21437\/Interspeech.2009-442"},{"issue":"3","key":"6_CR33","first-page":"169","volume":"13","author":"I. Poggi","year":"2000","unstructured":"Poggi, I., Pelachaud, C., De Rosisc, F.: Eye communication in a conversational 3D synthetic agent. AI communications\u00a013(3), 169\u2013181 (2000)","journal-title":"AI communications"},{"key":"6_CR34","unstructured":"Ekman, P.: About brows: Emotional and conversational signals. Human ethology: Claims and limits of a new discipline: contributions to the Colloquium, 169\u2013248 (1979)"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Cassell, J., Pelachaud, C., Badler, N., Steedman, M., Achorn, B., Becket, T., Douville, B., Prevost, S., Stone, M.: Animated conversation: rule-based generation of facial expression, gesture & spoken intonation for multiple conversational agents. In: Proceedings of the 21st annual conference on Computer graphics and interactive techniques, pp. 413\u2013420 (1994)","DOI":"10.1145\/192161.192272"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Raidt, S., Bailly, G., Elisei, F.: Analyzing and modeling gaze during face-to-face interaction. In: Proceedings of the International Conference on Auditory-Visual Speech Processing, AVSP 2007 (2007)","DOI":"10.1109\/WI-IATW.2007.33"},{"issue":"6","key":"6_CR37","doi-asserted-by":"publisher","first-page":"926","DOI":"10.3758\/BF03211929","volume":"60","author":"E. Vatikiotis-Bateson","year":"1998","unstructured":"Vatikiotis-Bateson, E., Eigsti, I., Yano, S., Munhall, K.: Eye movement of perceivers during audiovisual speech perception. Perception and Psychophysics\u00a060(6), 926\u2013940 (1998)","journal-title":"Perception and Psychophysics"},{"issue":"4","key":"6_CR38","doi-asserted-by":"publisher","first-page":"553","DOI":"10.3758\/BF03194582","volume":"65","author":"M. Par\u00e9","year":"2003","unstructured":"Par\u00e9, M., Richler, R., Ten, H., Munhall, K.: Gaze behavior in audiovisual speech perception: The influence of ocular fixations on the McGurk effect. Perception & psychophysics\u00a065(4), 553 (2003)","journal-title":"Perception & psychophysics"},{"key":"6_CR39","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1121\/1.426724","volume":"105","author":"A. Cutler","year":"1999","unstructured":"Cutler, A., Otake, T.: Pitch accent in spoken-word recognition in Japanese. The Journal of the Acoustical Society of America\u00a0105, 1877 (1999)","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"4","key":"6_CR40","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1073\/pnas.0408949102","volume":"102","author":"V. Wassenhove van","year":"2005","unstructured":"van Wassenhove, V., Grant, K., Poeppel, D.: Visual speech speeds up the neural processing of auditory speech. Proceedings of the National Academy of Sciences\u00a0102(4), 1181 (2005)","journal-title":"Proceedings of the National Academy of Sciences"}],"container-title":["Lecture Notes in Computer Science","Toward Autonomous, Adaptive, and Context-Aware Multimodal Interfaces. Theoretical and Practical Issues"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-18184-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T22:14:51Z","timestamp":1685916891000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-18184-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642181832","9783642181849"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-18184-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}