{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T16:10:32Z","timestamp":1746115832483,"version":"3.40.4"},"publisher-location":"New York, NY","reference-count":24,"publisher":"Springer New York","isbn-type":[{"type":"print","value":"9781461482796"},{"type":"electronic","value":"9781461482802"}],"license":[{"start":{"date-parts":[[2013,8,28]],"date-time":"2013-08-28T00:00:00Z","timestamp":1377648000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2013,8,28]],"date-time":"2013-08-28T00:00:00Z","timestamp":1377648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-1-4614-8280-2_21","type":"book-chapter","created":{"date-parts":[[2013,10,25]],"date-time":"2013-10-25T18:25:18Z","timestamp":1382725518000},"page":"241-247","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual Contribution to Word Prominence Detection in a Playful Interaction Setting"],"prefix":"10.1007","author":[{"given":"Martin","family":"Heckmann","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,8,28]]},"reference":[{"key":"21_CR1","unstructured":"Al\u00a0Moubayed, S., Beskow, J.: Effects of visual prominence cues on speech intelligibility. In: Proceedings of the International Conference on Auditory Visual Speech Process. (AVSP), vol.\u00a09, p.\u00a016. ISCA, Austin (2009)"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Beskow, J., Granstr\u00f6m, B., House, D.: Visual correlates to prominence in several expressive modes. In: Proceedings of INTERSPEECH, pp.\u00a01272\u20131275. ISCA (2006)","DOI":"10.21437\/Interspeech.2006-375"},{"key":"21_CR3","unstructured":"Black, A., Taylor, P., Caley, R.: The festival speech synthesis system. Tech. rep.\u00a0(1998)"},{"key":"21_CR4","volume-title":"Learning","author":"G. Bradski","year":"2008","unstructured":"Bradski, G., Kaehler, A.: Learning OpenCV: Computer vision with the OpenCV library O\u2019reilly (2008)"},{"issue":"3","key":"21_CR5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"Chih-Chung Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2, 27:1\u201327:27 (2011). Software available at http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvm","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"21_CR6","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1121\/1.2229005","volume":"120","author":"M. Cooke","year":"2006","unstructured":"Cooke, M., Barker, J., Cunningham, S., Shao, X.: An audio-visual corpus for speech perception and automatic speech recognition. J. Acoust. Soc. Am. 120, 2421 (2006)","journal-title":"J. Acoust. Soc. Am."},{"key":"21_CR7","volume-title":"Prosody for the eyes: Quantifying visual prosody using guided principal component analysis","author":"E. Cvejic","year":"2010","unstructured":"Cvejic, E., Kim, J., Davis, C., Gibert, G.: Prosody for the eyes: Quantifying visual prosody using guided principal component analysis. In: Proceedings of INTERSPEECH. ISCA (2010)"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Dohen, M., L\u0153venbruck, H., Harold, H., et\u00a0al.: Visual correlates of prosodic contrastive focus in french: Description and inter-speaker variability. In: Speech Prosody. Dresden, Germany (2006)","DOI":"10.21437\/SpeechProsody.2006-210"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Graf, H., Cosatto, E., Strom, V., Huang, F.: Visual prosody: Facial movements accompanying speech. In: International Conference on Automatic Face and Gesture Recognition, pp.\u00a0396\u2013401. IEEE (2002)","DOI":"10.1109\/AFGR.2002.1004186"},{"key":"21_CR10","volume-title":"Audio-visual evaluation and detection of word prominence in a human-machine interaction scenario","author":"M. Heckmann","year":"2012","unstructured":"Heckmann, M.: Audio-visual evaluation and detection of word prominence in a human-machine interaction scenario. In: Proceedings of INTERSPEECH. ISCA, Portland, OR (2012)"},{"key":"21_CR11","doi-asserted-by":"publisher","first-page":"1260","DOI":"10.1155\/S1110865702206150","volume":"11","author":"M. Heckmann","year":"2002","unstructured":"Heckmann, M., Berthommier, F., Kroschel, K.: Noise adaptive stream weighting in audio-visual speech recognition. EURASIP J. Applied Signal Process. 11, 1260\u20131273 (2002)","journal-title":"EURASIP J. Applied Signal Process."},{"issue":"5","key":"21_CR12","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1016\/j.specom.2010.08.006","volume":"53","author":"M. Heckmann","year":"2011","unstructured":"Heckmann, M., Domont, X., Joublin, F., Goerick, C.: A hierarchical framework for spectro-temporal feature extraction. Speech Comm. 53(5), 736\u2013752 (2011). DOI: 10.1016 \/j.specom.2010.08.006. Perceptual and Statistical Audition","journal-title":"Speech Comm."},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Heckmann, M., Gl\u00e4ser, C., Vaz, M., Rodemann, T., Joublin, F., Goerick, C.: Listen to the parrot: Demonstrating the quality of online pitch and formant extraction via feature-based resynthesis. In: Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). Nice (2008)","DOI":"10.1109\/IROS.2008.4650923"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Heckmann, M., Joublin, F., Goerick, C.: Combining rate and place information for robust pitch extraction. In: Proceedings of INTERSPEECH, pp.\u00a02765\u20132768. Antwerp (2007)","DOI":"10.21437\/Interspeech.2007-463"},{"issue":"1-2","key":"21_CR15","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.specom.2004.01.006","volume":"43","author":"J. Hirschberg","year":"2004","unstructured":"Hirschberg, J., Litman, D., Swerts, M.: Prosodic and other cues to speech recognition failures. Speech Communication 43(1-2), 155\u2013175 (2004)","journal-title":"Speech Communication"},{"key":"21_CR16","unstructured":"Kolossa, D., Zeiler, S., Vorwerk, A., Orglmeister, R.: Audiovisual speech recognition with missing or unreliable data. In: Proceedings of International Conference on Auditory Visual Speech Processing (AVSP) (2009)"},{"issue":"2","key":"21_CR17","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1111\/j.0963-7214.2004.01502010.x","volume":"15","author":"K. Munhall","year":"2004","unstructured":"Munhall, K., Jones, J., Callan, D., Kuratate, T., Vatikiotis-Bateson, E.: Visual prosody and speech intelligibility. Psychol. Sci. 15(2), 133 (2004)","journal-title":"Psychol. Sci."},{"issue":"5","key":"21_CR18","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1109\/89.861370","volume":"8","author":"E. N\u00f6th","year":"2000","unstructured":"N\u00f6th, E., Batliner, A., Kie\u00dfling, A., Kompe, R., Niemann, H.: Verbmobil: The use of prosody in the linguistic components of a speech understanding system. IEEE Trans. Speech and Audio Process. 8(5), 519\u2013532 (2000)","journal-title":"IEEE Trans. Speech and Audio Process."},{"issue":"9","key":"21_CR19","doi-asserted-by":"publisher","first-page":"1306","DOI":"10.1109\/JPROC.2003.817150","volume":"91","author":"G. Potamianos","year":"2003","unstructured":"Potamianos, G., Neti, C., Gravier, G., Garg, A., Senior, A.: Recent advances in the automatic recognition of audiovisual speech. Proc. IEEE 91(9), 1306\u20131326 (2003)","journal-title":"Proc. IEEE"},{"key":"21_CR20","volume-title":"Spontaneous speech: How people really talk and why engineers should care","author":"E. Shriberg","year":"2005","unstructured":"Shriberg, E.: Spontaneous speech: How people really talk and why engineers should care. In: Proceedings of EUROSPEECH, ISCA (2005)"},{"issue":"3","key":"21_CR21","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1162\/089120100561737","volume":"26","author":"A. Stolcke","year":"2000","unstructured":"Stolcke, A., Ries, K., Coccaro, N., Shriberg, E., Bates, R., Jurafsky, D., Taylor, P., Martin, R., Ess-Dykema, C., Meteer, M.: Dialogue act modeling for automatic tagging and recognition of conversational speech. Comput. ling. 26(3), 339\u2013373 (2000)","journal-title":"Comput. ling."},{"issue":"2","key":"21_CR22","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.wocn.2007.05.001","volume":"36","author":"M. Swerts","year":"2008","unstructured":"Swerts, M., Krahmer, E.: Facial expression and prosodic prominence: Effects of modality and facial area. J. Phonetics 36(2), 219\u2013238 (2008)","journal-title":"J. Phonetics"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Yoshida, T., Nakadai, K., Okuno, H.: Automatic speech recognition improved by two-layered audio-visual integration for robot audition. In: Proceedings of 9th IEEE-RAS International Conference on Humanoid Robots, pp.\u00a0604\u2013609. IEEE (2009)","DOI":"10.1109\/ICHR.2009.5379586"},{"key":"21_CR24","volume-title":"The HTK Book","author":"S. Young","year":"1995","unstructured":"Young, S., Odell, J., Ollason, D., Valtchev, V., Woodland, P.: The HTK Book. Cambridge University, Cambridge, United Kingdom (1995)"}],"container-title":["Natural Interaction with Robots, Knowbots and Smartphones"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4614-8280-2_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T18:23:13Z","timestamp":1746037393000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-4614-8280-2_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8,28]]},"ISBN":["9781461482796","9781461482802"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-1-4614-8280-2_21","relation":{},"subject":[],"published":{"date-parts":[[2013,8,28]]},"assertion":[{"value":"28 August 2013","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}