{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T02:27:56Z","timestamp":1792895276435,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,10,15]],"date-time":"2018-10-15T00:00:00Z","timestamp":1539561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"EPSRC","award":["EP\/L015897\/1"],"award-info":[{"award-number":["EP\/L015897\/1"]}]},{"name":"EPSRC","award":["EP\/M013774\/1"],"award-info":[{"award-number":["EP\/M013774\/1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,10,15]]},"DOI":"10.1145\/3240508.3240578","type":"proceedings-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T17:52:08Z","timestamp":1539885128000},"page":"292-301","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":238,"title":["Emotion Recognition in Speech using Cross-Modal Transfer in the Wild"],"prefix":"10.1145","author":[{"given":"Samuel","family":"Albanie","sequence":"first","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arsha","family":"Nagrani","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Vedaldi","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.122"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awp067"},{"key":"e_1_3_2_1_5_1","first-page":"892","volume-title":"Advances in Neural Information Processing Systems","author":"Aytar Y.","year":"2016","unstructured":"Y. Aytar , C. Vondrick , and A. Torralba . Soundnet: Learning sound representations from unlabeled video . In Advances in Neural Information Processing Systems , pages 892 -- 900 , 2016 . Y. Aytar, C. Vondrick, and A. Torralba. Soundnet: Learning sound representations from unlabeled video. In Advances in Neural Information Processing Systems, pages 892--900, 2016."},{"key":"e_1_3_2_1_6_1","volume-title":"See, hear, and read: Deep aligned representations. arXiv preprint arXiv:1706.00932","author":"Aytar Y.","year":"2017","unstructured":"Y. Aytar , C. Vondrick , and A. Torralba . See, hear, and read: Deep aligned representations. arXiv preprint arXiv:1706.00932 , 2017 . Y. Aytar, C. Vondrick, and A. Torralba. See, hear, and read: Deep aligned representations. arXiv preprint arXiv:1706.00932, 2017."},{"key":"e_1_3_2_1_7_1","first-page":"2654","volume-title":"Do deep nets really need to be deep? In Advances in neural information processing systems","author":"Ba J.","year":"2014","unstructured":"J. Ba and R. Caruana . Do deep nets really need to be deep? In Advances in neural information processing systems , pages 2654 -- 2662 , 2014 . J. Ba and R. Caruana. Do deep nets really need to be deep? In Advances in neural information processing systems, pages 2654--2662, 2014."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997627"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.3.295"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"e_1_3_2_1_11_1","volume-title":"LREC","author":"Batliner A.","year":"2004","unstructured":"A. Batliner , C. Hacker , S. Steidl , E. N\u00f8th , S. D'Arcy , M. J. Russell , and M. Wong . You stupid tin box-children interacting with the aibo robot: A cross-linguistic emotional speech corpus . In LREC , 2004 . A. Batliner, C. Hacker, S. Steidl, E. N\u00f8th, S. D'Arcy, M. J. Russell, and M. Wong. You stupid tin box-children interacting with the aibo robot: A cross-linguistic emotional speech corpus. In LREC, 2004."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"e_1_3_2_1_13_1","volume-title":"Ninth European Conference on Speech Communication and Technology","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 Ninth European Conference on Speech Communication and Technology , 2005 . F. Burkhardt, A. Paeschke, M. Rolfes, W. F. Sendlmeier, and B. Weiss. A database of german emotional speech. In Ninth European Conference on Speech Communication and Technology, 2005."},{"key":"e_1_3_2_1_14_1","volume-title":"Iemocap: Interactive emotional dyadic motion capture database. Language resources and evaluation, 42(4):335","author":"Busso C.","year":"2008","unstructured":"C. Busso , M. Bulut , C.-C. Lee , A. Kazemzadeh , E. Mower , S. Kim , J. N. Chang , S. Lee , and S. S. Narayanan . Iemocap: Interactive emotional dyadic motion capture database. Language resources and evaluation, 42(4):335 , 2008 . C. Busso, M. Bulut, C.-C. Lee, A. Kazemzadeh, E. Mower, S. Kim, J. N. Chang, S. Lee, and S. S. Narayanan. Iemocap: Interactive emotional dyadic motion capture database. Language resources and evaluation, 42(4):335, 2008."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027968"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.6"},{"key":"e_1_3_2_1_18_1","volume-title":"Workshop on Multi-view Lip-reading, ACCV","author":"Chung J. S.","year":"2016","unstructured":"J. S. Chung and A. Zisserman . Out of time: automated lip sync in the wild . In Workshop on Multi-view Lip-reading, ACCV , 2016 . J. S. Chung and A. Zisserman. Out of time: automated lip sync in the wild. In Workshop on Multi-view Lip-reading, ACCV, 2016."},{"key":"e_1_3_2_1_19_1","volume-title":"Moonshine: Distilling with cheap convolutions. arXiv preprint arXiv:1711.02613","author":"Crowley E. J.","year":"2017","unstructured":"E. J. Crowley , G. Gray , and A. Storkey . Moonshine: Distilling with cheap convolutions. arXiv preprint arXiv:1711.02613 , 2017 . E. J. Crowley, G. Gray, and A. Storkey. Moonshine: Distilling with cheap convolutions. arXiv preprint arXiv:1711.02613, 2017."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123371"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.02.006"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2324759"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.141"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997638"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.26"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"e_1_3_2_1_27_1","volume-title":"ISCA tutorial and research workshop (ITRW) on speech and emotion","author":"Douglas-Cowie E.","year":"2000","unstructured":"E. Douglas-Cowie , R. Cowie , and M. Schr\u00f6der . A new emotion database: considerations, sources and scope . In ISCA tutorial and research workshop (ITRW) on speech and emotion , 2000 . E. Douglas-Cowie, R. Cowie, and M. Schr\u00f6der. A new emotion database: considerations, sources and scope. In ISCA tutorial and research workshop (ITRW) on speech and emotion, 2000."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-42051-1_16"},{"issue":"4","key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1542\/peds.56.4.544","article-title":"Visual following and pattern discrimination of face-like stimuli by newborn infants","volume":"56","author":"Goren C. C.","year":"1975","unstructured":"C. C. Goren , M. Sarty , and P. Y. Wu . Visual following and pattern discrimination of face-like stimuli by newborn infants . Pediatrics , 56 ( 4 ): 544 -- 549 , 1975 . C. C. Goren, M. Sarty, and P. Y. Wu. Visual following and pattern discrimination of face-like stimuli by newborn infants. Pediatrics, 56(4):544--549, 1975.","journal-title":"Pediatrics"},{"key":"e_1_3_2_1_30_1","volume-title":"The development of emotion perception in face and voice during infancy. Restorative neurology and neuroscience, 28(2):219--236","author":"Grossmann T.","year":"2010","unstructured":"T. Grossmann . The development of emotion perception in face and voice during infancy. Restorative neurology and neuroscience, 28(2):219--236 , 2010 . T. Grossmann. The development of emotion perception in face and voice during infancy. Restorative neurology and neuroscience, 28(2):219--236, 2010."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123383"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1177\/1754073912451331"},{"key":"e_1_3_2_1_34_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton G.","year":"2015","unstructured":"G. Hinton , O. Vinyals , and J. Dean . Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 , 2015 . G. Hinton, O. Vinyals, and J. Dean. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143009"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/URTC.2017.8284175"},{"key":"e_1_3_2_1_38_1","volume-title":"Newborns' preferential tracking of face-like stimuli and its subsequent decline. Cognition, 40(1--2):1--19","author":"Johnson M. H.","year":"1991","unstructured":"M. H. Johnson , S. Dziurawiec , H. Ellis , and J. Morton . Newborns' preferential tracking of face-like stimuli and its subsequent decline. Cognition, 40(1--2):1--19 , 1991 . M. H. Johnson, S. Dziurawiec, H. Ellis, and J. Morton. Newborns' preferential tracking of face-like stimuli and its subsequent decline. Cognition, 40(1--2):1--19, 1991."},{"key":"e_1_3_2_1_39_1","volume-title":"On learning associations of faces and voices. arXiv preprint arXiv:1805.05553","author":"Kim C.","year":"2018","unstructured":"C. Kim , H. V. Shin , T.-H. Oh , A. Kaspar , M. Elgharib , and W. Matusik . On learning associations of faces and voices. arXiv preprint arXiv:1805.05553 , 2018 . C. Kim, H. V. Shin, T.-H. Oh, A. Kaspar, M. Elgharib, andW. Matusik. On learning associations of faces and voices. arXiv preprint arXiv:1805.05553, 2018."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123353"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993151"},{"key":"e_1_3_2_1_42_1","volume-title":"Transfer learning for improving speech emotion classification accuracy. arXiv preprint arXiv:1801.06353","author":"Latif S.","year":"2018","unstructured":"S. Latif , R. Rana , S. Younis , J. Qadir , and J. Epps . Transfer learning for improving speech emotion classification accuracy. arXiv preprint arXiv:1801.06353 , 2018 . S. Latif, R. Rana, S. Younis, J. Qadir, and J. Epps. Transfer learning for improving speech emotion classification accuracy. arXiv preprint arXiv:1801.06353, 2018."},{"key":"e_1_3_2_1_43_1","volume-title":"Fifteenth Annual Conference of the International Speech Communication Association","author":"Li J.","year":"2014","unstructured":"J. Li , R. Zhao , J.-T. Huang , and Y. Gong . Learning small-size dnn with outputdistribution- based criteria . In Fifteenth Annual Conference of the International Speech Communication Association , 2014 . J. Li, R. Zhao, J.-T. Huang, and Y. Gong. Learning small-size dnn with outputdistribution- based criteria. In Fifteenth Annual Conference of the International Speech Communication Association, 2014."},{"key":"e_1_3_2_1_44_1","volume-title":"Ldc emotional prosody speech transcripts database","author":"Liberman M.","year":"2002","unstructured":"M. Liberman , K. Davis , M. Grossman , N. Martey , and J. Bell . Ldc emotional prosody speech transcripts database . University of Pennsylvania , Linguistic data consortium, 2002 . M. Liberman, K. Davis, M. Grossman, N. Martey, and J. Bell. Ldc emotional prosody speech transcripts database. University of Pennsylvania, Linguistic data consortium, 2002."},{"key":"e_1_3_2_1_45_1","volume-title":"Exploring the limits of weakly supervised pretraining. arXiv preprint arXiv:1805.00932","author":"Mahajan D.","year":"2018","unstructured":"D. Mahajan , R. Girshick , V. Ramanathan , K. He , M. Paluri , Y. Li , A. Bharambe , and L. van der Maaten . Exploring the limits of weakly supervised pretraining. arXiv preprint arXiv:1805.00932 , 2018 . D. Mahajan, R. Girshick, V. Ramanathan, K. He, M. Paluri, Y. Li, A. Bharambe, and L. van der Maaten. Exploring the limits of weakly supervised pretraining. arXiv preprint arXiv:1805.00932, 2018."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.21"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2006.145"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2713783"},{"key":"e_1_3_2_1_52_1","volume-title":"The effect of position in utterance on speech segment duration in english. The journal of the Acoustical Society of America, 54(5):1235--1247","author":"Oller D. K.","year":"1973","unstructured":"D. K. Oller . The effect of position in utterance on speech segment duration in english. The journal of the Acoustical Society of America, 54(5):1235--1247 , 1973 . D. K. Oller. The effect of position in utterance on speech segment duration in english. The journal of the Acoustical Society of America, 54(5):1235--1247, 1973."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953216"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1352088"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10919-005-7720-z"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.10.005"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.05.006"},{"key":"e_1_3_2_1_59_1","volume-title":"Deep learning is robust to massive label noise. arXiv preprint arXiv:1705.10694","author":"Rolnick D.","year":"2017","unstructured":"D. Rolnick , A. Veit , S. Belongie , and N. Shavit . Deep learning is robust to massive label noise. arXiv preprint arXiv:1705.10694 , 2017 . D. Rolnick, A. Veit, S. Belongie, and N. Shavit. Deep learning is robust to massive label noise. arXiv preprint arXiv:1705.10694, 2017."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.8"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2007.05.001"},{"key":"e_1_3_2_1_62_1","volume-title":"British Machine Vision Conference (BMVC)","author":"Wiles O.","year":"2018","unstructured":"O. Wiles , A. S. Koepke , and A. Zisserman . Self-supervised learning of a facial attribute embedding from video . In British Machine Vision Conference (BMVC) , 2018 . O. Wiles, A. S. Koepke, and A. Zisserman. Self-supervised learning of a facial attribute embedding from video. In British Machine Vision Conference (BMVC), 2018."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830595"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-015-0822-0"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163986"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3130858"}],"event":{"name":"MM '18: ACM Multimedia Conference","location":"Seoul Republic of Korea","acronym":"MM '18","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 26th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240578","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3240508.3240578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:57:34Z","timestamp":1750208254000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240578"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,15]]},"references-count":66,"alternative-id":["10.1145\/3240508.3240578","10.1145\/3240508"],"URL":"https:\/\/doi.org\/10.1145\/3240508.3240578","relation":{},"subject":[],"published":{"date-parts":[[2018,10,15]]},"assertion":[{"value":"2018-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}