{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:20:32Z","timestamp":1762521632862},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/icassp.2013.6638338","type":"proceedings-article","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T23:19:46Z","timestamp":1383088786000},"page":"3647-3651","source":"Crossref","is-referenced-by-count":3,"title":["Speaker trait characterization in web videos: Uniting speech, language, and facial features"],"prefix":"10.1109","author":[{"given":"Felix","family":"Weninger","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudia","family":"Wagner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Wollmer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bjorn","family":"Schuller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Louis-Philippe","family":"Morency","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"The HTK Book Version 3 4","year":"2006","author":"young","key":"19"},{"journal-title":"Integrating Audio and Vision for Robust Automatic Gender Recognition","year":"2008","author":"pronobis","key":"17"},{"key":"18","article-title":"YouTube movie reviews: In cross, and open-domain sentiment analysis in an audiovisual context","author":"wollmer","year":"2013","journal-title":"IEEE Intelligent Systems Magazine Special Issue on Concept-Level Opinion and Sentiment Analysis"},{"key":"15","doi-asserted-by":"crossref","first-page":"1381","DOI":"10.21437\/Interspeech.2010-421","article-title":"Can conversational word usage be used to predict speaker demographics","author":"gillick","year":"2010","journal-title":"Proc of Interspeech"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1117\/12.774687"},{"key":"13","article-title":"The identity of bloggers: Openness and gender in personal weblogs","author":"nowson","year":"2006","journal-title":"Proceedings of the AAAI Spring Symposia on Computational Approaches to Analyzing Weblogs"},{"key":"14","doi-asserted-by":"crossref","first-page":"545","DOI":"10.4018\/978-1-60960-741-8.ch032","article-title":"Using liwc and coh-metrix to investigate gender differences in linguistic styles","author":"bell","year":"2012","journal-title":"Applied Natural Language Processing Identification Investigation and Resolution P McCarthy and C Boonthum-Denecke Eds"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239227"},{"key":"12","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1007\/978-3-642-25446-8_6","article-title":"Analyzing facial behavioral features from videos","author":"hadid","year":"2011","journal-title":"Human Behavior Understanding"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.54.101601.145041"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1177\/0261927X09351676"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1108\/eb046814"},{"key":"24","article-title":"LSTM-modeling of continuous emotions in an audiovisual affect recognition framework","author":"wollmer","year":"2012","journal-title":"Image and Vision Computing"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1145\/1656274.1656278"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2005.05.001"},{"key":"3","first-page":"89","article-title":"Semantic speech tagging: Towards combined analysis of speaker traits","author":"schuller","year":"2011","journal-title":"Proceedings AES 42nd International Conference"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-010-9064-2"},{"key":"10","doi-asserted-by":"crossref","DOI":"10.1117\/12.851424","article-title":"Automated person categorization for video surveillance using soft biometrics","author":"demirkus","year":"2010","journal-title":"SPIE Biometric Technology for Human Identification Conf"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367263"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.02.005"},{"key":"6","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-169","article-title":"Age estimation from telephone speech using ivectors","author":"bahari","year":"2012","journal-title":"Proc of Interspeech"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2012.15"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2192211"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2008.4760995"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.208"}],"event":{"name":"ICASSP 2013 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2013,5,26]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2013,5,31]]}},"container-title":["2013 IEEE International Conference on Acoustics, Speech and Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6619549\/6637585\/06638338.pdf?arnumber=6638338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T22:45:26Z","timestamp":1646952326000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6638338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2013.6638338","relation":{},"subject":[],"published":{"date-parts":[[2013,5]]}}}