{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:27:48Z","timestamp":1783438068233,"version":"3.54.6"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2014,12,1]],"date-time":"2014-12-01T00:00:00Z","timestamp":1417392000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61272211"],"award-info":[{"award-number":["61272211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61170126"],"award-info":[{"award-number":["61170126"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Six Talent Peaks Foundation of Jiangsu Province"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/tmm.2014.2360798","type":"journal-article","created":{"date-parts":[[2014,9,29]],"date-time":"2014-09-29T19:29:26Z","timestamp":1412018966000},"page":"2203-2213","source":"Crossref","is-referenced-by-count":507,"title":["Learning Salient Features for Speech Emotion <newline\/>Recognition Using Convolutional <newline\/>Neural Networks"],"prefix":"10.1109","volume":"16","author":[{"given":"Qirong","family":"Mao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengwei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongzhao","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2058095"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2162405"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082328"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref31","first-page":"808","article-title":"Disentangling factors of variation for facial expression recognition","volume":"7577","author":"rifai","year":"2012","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9172-2"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1007\/978-3-642-24571-8_54","article-title":"Investigating glottal parameters and Teager energy operators in emotion recognition","volume":"6975","author":"sun","year":"2011","journal-title":"Affective Comput Intell Interaction Lecture Notes Comput Sci"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"ref35","author":"steidl","year":"2009","journal-title":"Automatic Classification of Emotion-Related User States in Spontaneous Children's Speech"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2234729"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.04.003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/AIPR.2010.5759701"},{"key":"ref12","first-page":"53","article-title":"Speaker-dependent audio-visual emotion recognition","author":"haq","year":"2009","journal-title":"Proc Int Conf Auditory-Visual Speech Process"},{"key":"ref13","first-page":"1013","article-title":"Fusion of global statistical and segmental spectral features for speech emotion recognition","volume":"2","author":"hu","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654984"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9150-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9139-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707732"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.838534"},{"key":"ref19","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"Proc Advances Neural Inform Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74171-8_101"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"2115","DOI":"10.1007\/s00521-011-0643-1","article-title":"Speech emotion recognition using FCBF feature selection method and GA-optimized fuzzy ARTMAP neural network","volume":"21","author":"davood","year":"2012","journal-title":"Neural Comput Appl"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1504\/IJAACS.2008.019799"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.21437\/Interspeech.2005-446","article-title":"A database of German Emotional Speech","author":"burkhardt","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-011-9624-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854517"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349350"},{"key":"ref7","first-page":"1695","article-title":"Design, recording and verification of a Danish emotional speech database","author":"engberg","year":"1997","journal-title":"Proc 5th Eur Conf Speech Commun Technol"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E93.D.2324"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.008"},{"key":"ref46","first-page":"457","article-title":"Emotion recognition in Chinese natural speech by combining prosody and voice quality features","author":"zhang","year":"2008","journal-title":"Proc Int Symp Neural Networks"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2051872"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886310"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s00521-012-0814-8","article-title":"Modular neural-SVM scheme for speech emotion recognition using ANOVA feature selection method","volume":"23","author":"mansour","year":"2013","journal-title":"Neural Comput Appl"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CMCSN.2012.24"},{"key":"ref21","first-page":"1225","article-title":"Combining classifiers with diverse feature sets for robust speaker independent emotion recognition","author":"lugger","year":"2009","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.16"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288834"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843610002088"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"ref43","first-page":"1","article-title":"Feature learning in deep neural networks - Studies on speech recognition tasks","author":"yu","year":"2013","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.004"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/6955763\/06913013.pdf?arnumber=6913013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,18]],"date-time":"2022-04-18T06:34:40Z","timestamp":1650263680000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6913013\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":47,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2014.2360798","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,12]]}}}