{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T11:01:04Z","timestamp":1777892464531,"version":"3.51.4"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan","award":["2016YFB1001200"],"award-info":[{"award-number":["2016YFB1001200"]}]},{"name":"Innovation Method Fund of China","award":["2016IM010200"],"award-info":[{"award-number":["2016IM010200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural and Science Foundation of China","doi-asserted-by":"crossref","award":["61521002"],"award-info":[{"award-number":["61521002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Tiangong Institute for Intelligent Computing, Tsinghua University, Beijing, China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/tmm.2018.2887016","type":"journal-article","created":{"date-parts":[[2018,12,17]],"date-time":"2018-12-17T20:23:43Z","timestamp":1545078223000},"page":"1853-1866","source":"Crossref","is-referenced-by-count":19,"title":["Inferring Emotions From Large-Scale Internet Voice Data"],"prefix":"10.1109","volume":"21","author":[{"given":"Jia","family":"Jia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3472-1434","authenticated-orcid":false,"given":"Suping","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufeng","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5511-7968","authenticated-orcid":false,"given":"Boya","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanbo","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-011-9624-z"},{"key":"ref71","first-page":"857","article-title":"Can we understand van gogh's mood?learning to infer affects from images in social networks","author":"jia","year":"0","journal-title":"Proc 20th ACM Int Conf Multimedia"},{"key":"ref70","first-page":"1617","article-title":"Emotions recognition by speechand facial expressions analysis","author":"emerich","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref39","first-page":"122","article-title":"From tweets to polls: Linking text sentiment to public opinion time series","author":"o\u2019connor","year":"0","journal-title":"Proc 4th Int AAAI Conf Weblogs Social Media"},{"key":"ref38","first-page":"1","article-title":"Detecting sadness in 140 characters: Sentiment analysis and mourning michael jackson on twitter","volume":"3","author":"kim","year":"2009","journal-title":"Web Ecology"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2400917"},{"key":"ref32","first-page":"27","article-title":"Emotex: Detecting emotions in twitter messages","author":"hasan","year":"0","journal-title":"Proc ASE BIGDATA\/SOCIALCOM\/CYBERSECURITY"},{"key":"ref31","first-page":"48","article-title":"Multi-class twitter emotion classification: A new approach","volume":"4","author":"cbalabantaray","year":"2012","journal-title":"Int J Appl Inf Syst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344564"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396330"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344555"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2617741"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177462"},{"key":"ref60","first-page":"2362","article-title":"Context-sensitive multimodal emotion recognition from speech and facial expression using bidirectional LSTM modeling","author":"w\u00f6llmer","year":"0","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref62","first-page":"4860","article-title":"A multi-stream ASR framework for BLSTM modeling of conversational speech","author":"w\u00f6llmer","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"ref63","first-page":"36","article-title":"A novel bottleneck-BLSTM front-end for feature-level context modeling in conversational speech recognition","author":"w\u00f6llmer","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654984"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"ref65","first-page":"9","article-title":"Efficient backprop","author":"lecun","year":"0","journal-title":"Proc Neural Netw Tricks of the Trade"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854478"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344669"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873965"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.23"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.2307\/2685209"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344596"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISDA.2015.7489165"},{"key":"ref20","article-title":"Feature learning in deep neural networks - studies on speech recognition tasks","author":"yu","year":"0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2007.4412916"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344669"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2991\/iccasm.2012.311"},{"key":"ref23","first-page":"65","article-title":"Speech based emotion recognition with gaussian mixture model","volume":"1","author":"thapliyal","year":"2012","journal-title":"Int J Adv Res Comput Eng Technol"},{"key":"ref26","first-page":"223","article-title":"Speech emotion recognition using deep neural network and extreme learning machine","author":"han","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638116"},{"key":"ref50","first-page":"537","article-title":"Nearly defect-free f0 trajectory extraction for expressive speech modifications based on straight","author":"kawahara","year":"0","journal-title":"Proc Eur Conf Speech Communication and Technology EUROSPEECH"},{"key":"ref51","author":"mei","year":"1996","journal-title":"Tongyici Cilin (Version 2)"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref58","first-page":"873","article-title":"Sparse deep belief net model for visual area v2","author":"lee","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref57","first-page":"37","article-title":"Autoencoders, unsupervised learning, and deep architectures","author":"baldi","year":"0","journal-title":"Proc ICML Workshop Unsupervised Transfer Learn"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2011.48"},{"key":"ref55","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref54","first-page":"306","article-title":"How do your friends on social media disclose your emotions","author":"yang","year":"0","journal-title":"Proc 28th AAAI Conf Artif Intell"},{"key":"ref53","first-page":"1967","article-title":"Multimodal learning with deep boltzmann machines","volume":"15","author":"srivastava","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref52","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2012","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5815\/ijigsp.2013.09.02"},{"key":"ref11","first-page":"1","article-title":"A fisher discriminant framework based on kernel entropy component analysis for feature extraction and emotion recognition","author":"gao","year":"0","journal-title":"Proc IEEE Int Conf Multimedia Expo Workshops"},{"key":"ref40","first-page":"2365","article-title":"Modeling public mood and emotion: Twitter sentiment and socio-economic phenomena","volume":"44","author":"bollen","year":"2009","journal-title":"Comput Sci"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2264274"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2593685"},{"key":"ref14","first-page":"667","article-title":"Spatio-temporal dynamics of online memes:A study of geo-tagged tweets","author":"kamath","year":"0","journal-title":"Proc Int Conf World Wide Web"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/EMEIT.2011.6023178"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997632"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TSA.2004.838534","article-title":"Toward detecting emotions in spoken dialogs","volume":"13","author":"lee","year":"2005","journal-title":"IEEE Trans Speech Audio Process"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_58"},{"key":"ref4","first-page":"6","article-title":"Speech emotion recognition using support vector machine","volume":"1","author":"pan","year":"2013","journal-title":"Int J Smart Home"},{"key":"ref3","first-page":"401","article-title":"Hidden Markov model-based speech emotion recognition","volume":"1","author":"schuller","year":"0","journal-title":"Proc Int Conf Multimedia Expo"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2485538"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2598092"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881703"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/UIC-ATC-ScalCom-CBDCom-IoP-SmartWorld.2016.0133"},{"key":"ref46","article-title":"Analysis and conversion for affective speech","author":"cui","year":"2007"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552890"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-04114-8_28"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967217"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2010.12.007"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806319"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8743377\/08579582.pdf?arnumber=8579582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:50:18Z","timestamp":1657745418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8579582\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":72,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2887016","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7]]}}}