{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T21:56:35Z","timestamp":1767650195009,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2014,11,12]],"date-time":"2014-11-12T00:00:00Z","timestamp":1415750400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004963","name":"Seventh Framework Programme","doi-asserted-by":"publisher","award":["230331-PROPEREMO"],"award-info":[{"award-number":["230331-PROPEREMO"]}],"id":[{"id":"10.13039\/501100004963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"publisher","award":["51NF40-104897"],"award-info":[{"award-number":["51NF40-104897"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2014,11,12]]},"DOI":"10.1145\/2663204.2666271","type":"proceedings-article","created":{"date-parts":[[2014,11,17]],"date-time":"2014-11-17T15:46:48Z","timestamp":1416239208000},"page":"473-480","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Emotion Recognition in the Wild"],"prefix":"10.1145","author":[{"given":"Fabien","family":"Ringeval","sequence":"first","affiliation":[{"name":"Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shahin","family":"Amiriparian","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Eyben","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Klaus","family":"Scherer","sequence":"additional","affiliation":[{"name":"University of Geneva, Geneva, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bj\u00f6rn","family":"Schuller","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t M\u00fcnchen \/ Imperial College London, Munich \/ London, England UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2014,11,12]]},"reference":[{"key":"e_1_3_2_1_1_1","series-title":"Lecture Notes in Computer Science","volume-title":"Maximising Audiovisual Correlation with Automatic Lip Tracking and Vowel Based Segmentations. Biometric ID Management and Multimodal Communication, joint COST 2101 and 2102 International Conference","author":"Abel A.","year":"2009","unstructured":"A. Abel , A. Hussain , Q. D. Nguyen , F. Ringeval , M. Chetouani , and M. Milgram . Maximising Audiovisual Correlation with Automatic Lip Tracking and Vowel Based Segmentations. Biometric ID Management and Multimodal Communication, joint COST 2101 and 2102 International Conference , Madrid, Spain , September 16--18 2009 , Lecture Notes in Computer Science , 5707:65--72, 2009. A. Abel, A. Hussain, Q. D. Nguyen, F. Ringeval, M. Chetouani, and M. Milgram. Maximising Audiovisual Correlation with Automatic Lip Tracking and Vowel Based Segmentations. Biometric ID Management and Multimodal Communication, joint COST 2101 and 2102 International Conference, Madrid, Spain, September 16--18 2009, Lecture Notes in Computer Science, 5707:65--72, 2009."},{"issue":"5","key":"e_1_3_2_1_2_1","first-page":"1161","article-title":"anziger, M. Mortillaro, and K","volume":"12","author":"T.","year":"2012","unstructured":"T. B\\ \" anziger, M. Mortillaro, and K . Scherer. Introducing the Geneva Multimodal Expression Corpus for Experimental Research on Emotion Perception. Emotion , 12 ( 5 ): 1161 -- 1179 , 2012 . T. B\\\"anziger, M. Mortillaro, and K. Scherer. Introducing the Geneva Multimodal Expression Corpus for Experimental Research on Emotion Perception. Emotion, 12(5):1161--1179, 2012.","journal-title":"Scherer. Introducing the Geneva Multimodal Expression Corpus for Experimental Research on Emotion Perception. Emotion"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2326393"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.21437\/Interspeech.2005-446","volume-title":"Proc. of INTERSPEECH 2005","author":"Burkhardt F.","year":"2005","unstructured":"F. Burkhardt , A. Paeschke , M. Rolfes , W. F. Sendlmeier , and B. Weiss . A Database of German Emotional Speech . In Proc. of INTERSPEECH 2005 , pages 1517 -- 1520 , Lisbon, Portugal , 2005 . ISCA. F. Burkhardt, A. Paeschke, M. Rolfes, W. F. Sendlmeier, and B. Weiss. A Database of German Emotional Speech. In Proc. of INTERSPEECH 2005, pages 1517--1520, Lisbon, Portugal, 2005. ISCA."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2666275"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2531739"},{"key":"e_1_3_2_1_8_1","first-page":"2106","volume-title":"Evaluation Protocol and Benchmark. In Proc. of ICCV Workshops 2011","author":"Dhall A.","year":"2011","unstructured":"A. Dhall , R. Goecke , S. Lucey , and T. Gedeon . Static Facial Expression Analysis in Tough Conditions: Data , Evaluation Protocol and Benchmark. In Proc. of ICCV Workshops 2011 , pages 2106 -- 2112 , Barcelona, Spain , November 2011 . IEEE. A. Dhall, R. Goecke, S. Lucey, and T. Gedeon. Static Facial Expression Analysis in Tough Conditions: Data, Evaluation Protocol and Benchmark. In Proc. of ICCV Workshops 2011, pages 2106--2112, Barcelona, Spain, November 2011. IEEE."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.26"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","first-page":"2044","DOI":"10.21437\/Interspeech.2013-484","volume-title":"Proc. of INTERSPEECH 2013","author":"Eyben F.","year":"2013","unstructured":"F. Eyben , F. Weninger , and B. Schuller . Affect Recognition in Real-Life Acoustic Conditions -- A New Perspective on Feature Selection . In Proc. of INTERSPEECH 2013 , pages 2044 -- 2048 , Lyon, France , August 2013 . ISCA. F. Eyben, F. Weninger, and B. Schuller. Affect Recognition in Real-Life Acoustic Conditions -- A New Perspective on Feature Selection. In Proc. of INTERSPEECH 2013, pages 2044--2048, Lyon, France, August 2013. ISCA."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2008.4607572"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1656274.1656278"},{"key":"e_1_3_2_1_15_1","volume-title":"November","author":"Hermansky H.","year":"1990","unstructured":"H. Hermansky . Perceptual Linear Predictive (PLP) Analysis of Speech . Journal of the Acoustical Society of America (JASA), 87(4):1738--1752 , November 1990 . H. Hermansky. Perceptual Linear Predictive (PLP) Analysis of Speech. Journal of the Acoustical Society of America (JASA), 87(4):1738--1752, November 1990."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","first-page":"2794","DOI":"10.21437\/Interspeech.2010-739","volume-title":"Proc. of INTERSPEECH 2010","author":"Schuller B.","year":"2010","unstructured":"B. Schuller , S. Steidl , A. Batliner , F. Burkhardt , L. Devillers , C. M\u00fcller , and S. Narayanan . The INTERSPEECH 2010 Paralinguistic Challenge . In Proc. of INTERSPEECH 2010 , pages 2794 -- 2797 , Makuhari, Japan , 2010 . ISCA. B. Schuller, S. Steidl, A. Batliner, F. Burkhardt, L. Devillers, C. M\u00fcller, and S. Narayanan. The INTERSPEECH 2010 Paralinguistic Challenge. In Proc. of INTERSPEECH 2010, pages 2794--2797, Makuhari, Japan, 2010. ISCA."},{"key":"e_1_3_2_1_19_1","volume-title":"Proc. of INTERSPEECH 2014","author":"Schuller B.","year":"2014","unstructured":"B. Schuller , S. Steidl , A. Batliner , J. Epps , F. Eyben , F. Ringeval , E. Marchi , and Y. Zhang . The INTERSPEECH 2014 Computational Paralinguistics Challenge: Cognitive & Physical Load . In Proc. of INTERSPEECH 2014 , Singapore, Singapore , September 2014 . ISCA. B. Schuller, S. Steidl, A. Batliner, J. Epps, F. Eyben, F. Ringeval, E. Marchi, and Y. Zhang. The INTERSPEECH 2014 Computational Paralinguistics Challenge: Cognitive & Physical Load. In Proc. of INTERSPEECH 2014, Singapore, Singapore, September 2014. ISCA."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","first-page":"148","DOI":"10.21437\/Interspeech.2013-56","volume-title":"The INTERSPEECH 2013 Computational Paralinguistics Challenge: Social Signals, Conflict, Emotion, Autism. In Proc. of INTERSPEECH 2013","author":"Schuller B.","year":"2013","unstructured":"B. Schuller , S. Steidl , A. Batliner , A. Vinciarelli , K. Scherer , F. Ringeval , M. Chetouani , F. Weninger , F. Eyben , E. Marchi , M. Mortillaro , H. Salamin , A. Polychroniou , F. Valente , and S. Kim . The INTERSPEECH 2013 Computational Paralinguistics Challenge: Social Signals, Conflict, Emotion, Autism. In Proc. of INTERSPEECH 2013 , pages 148 -- 152 , Lyon, France , August 2013 . ISCA. B. Schuller, S. Steidl, A. Batliner, A. Vinciarelli, K. Scherer, F. Ringeval, M. Chetouani, F. Weninger, F. Eyben, E. Marchi, M. Mortillaro, H. Salamin, A. Polychroniou, F. Valente, and S. Kim. The INTERSPEECH 2013 Computational Paralinguistics Challenge: Social Signals, Conflict, Emotion, Autism. In Proc. of INTERSPEECH 2013, pages 148--152, Lyon, France, August 2013. ISCA."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388758"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"e_1_3_2_1_23_1","volume-title":"May","author":"Weninger F.","year":"2013","unstructured":"F. Weninger , F. Eyben , B. W. Schuller , M. Mortillaro , and K. R. Scherer . On the Acoustics of Emotion in Audio: What Speech, Music and Sound have in Common. Frontiers in Emotion Science, 4(Article ID 292):1--12 , May 2013 . F. Weninger, F. Eyben, B. W. Schuller, M. Mortillaro, and K. R. Scherer. On the Acoustics of Emotion in Audio: What Speech, Music and Sound have in Common. Frontiers in Emotion Science, 4(Article ID 292):1--12, May 2013."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.75"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1110"},{"key":"e_1_3_2_1_26_1","first-page":"2879","volume-title":"Proc. of CVPR 2012","author":"Zhu X.","year":"2012","unstructured":"X. Zhu and D. Ramanan . Face Detection, Pose Estimation, and Landmark Localization in the Wild . In Proc. of CVPR 2012 , pages 2879 -- 2886 , Providence, RI, USA , 2012 . IEEE. X. Zhu and D. Ramanan. Face Detection, Pose Estimation, and Landmark Localization in the Wild. In Proc. of CVPR 2012, pages 2879--2886, Providence, RI, USA, 2012. IEEE."}],"event":{"name":"ICMI '14: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Istanbul Turkey","acronym":"ICMI '14"},"container-title":["Proceedings of the 16th International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2663204.2666271","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2663204.2666271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:13:47Z","timestamp":1750227227000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2663204.2666271"}},"subtitle":["Incorporating Voice and Lip Activity in Multimodal Decision-Level Fusion"],"short-title":[],"issued":{"date-parts":[[2014,11,12]]},"references-count":26,"alternative-id":["10.1145\/2663204.2666271","10.1145\/2663204"],"URL":"https:\/\/doi.org\/10.1145\/2663204.2666271","relation":{},"subject":[],"published":{"date-parts":[[2014,11,12]]},"assertion":[{"value":"2014-11-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}