{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T12:43:32Z","timestamp":1771677812427,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,10,15]]},"DOI":"10.1145\/3266302.3266306","type":"proceedings-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T14:19:29Z","timestamp":1539872369000},"page":"99-105","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Learning an Arousal-Valence Speech Front-End Network using Media Data In-the-Wild for Emotion Recognition"],"prefix":"10.1145","author":[{"given":"Chih-Chuan","family":"Lu","sequence":"first","affiliation":[{"name":"National Tsing Hua University & MOST Joint Research Center for AI Technology and All Vista Healthcare, Hsinchu City, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeng-Lin","family":"Li","sequence":"additional","affiliation":[{"name":"National Tsing Hua University & MOST Joint Research Center for AI Technology and All Vista Healthcare, Hsinchu City, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Chun","family":"Lee","sequence":"additional","affiliation":[{"name":"National Tsing Hua University & MOST Joint Research Center for AI Technology and All Vista Healthcare, Hsinchu City, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International journal of computer science and Information Security (IJCSIS) 6, 3 (December","author":"Anusuya MA","year":"2009"},{"key":"e_1_3_2_1_2_1","volume-title":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 965--969","author":"Asgari M."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2326393"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"e_1_3_2_1_6_1","volume-title":"Medical Imaging 2017: Computer-Aided Diagnosis","author":"Chen Quan"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273615"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.90"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-868"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the International Speech Communication Association (Interspeech).","author":"Han Kun","year":"2014"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPIN.2017.8049931"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Chin-Lan Huang Cindy K Chung Natalie Hui Yi-Cheng Lin Yi-Tai Seih Ben CP Lam Wei-Chuan Chen Michael H Bond and James W Pennebaker. 2012. The development of the Chinese linguistic inquiry and word count dictionary. Chinese Journal of Psychology (2012).  Chin-Lan Huang Cindy K Chung Natalie Hui Yi-Cheng Lin Yi-Tai Seih Ben CP Lam Wei-Chuan Chen Michael H Bond and James W Pennebaker. 2012. The development of the Chinese linguistic inquiry and word count dictionary. Chinese Journal of Psychology (2012).","DOI":"10.4018\/978-1-60960-741-8.ch012"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3354-x"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85563-7_30"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIP.2012.6232924"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123353"},{"key":"e_1_3_2_1_18_1","volume-title":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing. 3677--3681","author":"Kim Y."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Kingma Diederik P","year":"2015"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1294885.1294891"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.05.264"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1108\/07378831311329068"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/962754.963031"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952290"},{"key":"e_1_3_2_1_26_1","unstructured":"Andrej Luneski Panagiotis D Bamidis and Madga Hitoglou-Antoniadou. 2008. Affective computing and medical informatics: state of the art in emotion-aware medical applications. Studies in health technology and informatics 136 (2008) 517.  Andrej Luneski Panagiotis D Bamidis and Madga Hitoglou-Antoniadou. 2008. Affective computing and medical informatics: state of the art in emotion-aware medical applications. Studies in health technology and informatics 136 (2008) 517."},{"key":"e_1_3_2_1_27_1","volume-title":"Applied Computing, Computer Science, and Advanced Communication","author":"Luo Qi"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.11"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2236291"},{"key":"e_1_3_2_1_30_1","volume-title":"Cross-lingual and Multilingual Speech Emotion Recognition on English and French. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).","author":"Neumann Michael","year":"2018"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000011"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2016.01.007"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Hoo-Chang Shin Holger R Roth Mingchen Gao Le Lu Ziyue Xu Isabella Nogues Jianhua Yao Daniel Mollura and Ronald M Summers. 2016. Deep convolutional neural networks for computer-aided detection: CNN architectures dataset characteristics and transfer learning. IEEE transactions on medical imaging 35 5 (2016) 1285--1298.  Hoo-Chang Shin Holger R Roth Mingchen Gao Le Lu Ziyue Xu Isabella Nogues Jianhua Yao Daniel Mollura and Ronald M Summers. 2016. Deep convolutional neural networks for computer-aided detection: CNN architectures dataset characteristics and transfer learning. IEEE transactions on medical imaging 35 5 (2016) 1285--1298.","DOI":"10.1109\/TMI.2016.2528162"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Simonyan Karen","year":"2015"},{"key":"e_1_3_2_1_35_1","first-page":"242","article-title":"Transfer Learning. In Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques: Algorithms, Methods, and Techniques, Emilio Soria Olivas (Ed.). IGI Global","volume":"11","author":"Torrey Lisa","year":"2009","journal-title":"Chapter"},{"key":"e_1_3_2_1_36_1","unstructured":"Jason Yosinski Jeff Clune Yoshua Bengio and Hod Lipson. 2014. How transferable are features in deep neural networks?. In Advances in neural information processing systems. 3320--3328.   Jason Yosinski Jeff Clune Yoshua Bengio and Hod Lipson. 2014. How transferable are features in deep neural networks?. In Advances in neural information processing systems. 3320--3328."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1066"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344669"},{"key":"e_1_3_2_1_39_1","unstructured":"Bolei Zhou Agata Lapedriza Jianxiong Xiao Antonio Torralba and Aude Oliva. 2014. Learning deep features for scene recognition using places database. In Advances in neural information processing systems. 487--495.   Bolei Zhou Agata Lapedriza Jianxiong Xiao Antonio Torralba and Aude Oliva. 2014. Learning deep features for scene recognition using places database. In Advances in neural information processing systems. 487--495."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1129"}],"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 2018 on Audio\/Visual Emotion Challenge and Workshop"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3266302.3266306","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3266302.3266306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:26:51Z","timestamp":1750278411000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3266302.3266306"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,15]]},"references-count":40,"alternative-id":["10.1145\/3266302.3266306","10.1145\/3266302"],"URL":"https:\/\/doi.org\/10.1145\/3266302.3266306","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"}}]}}