{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:19:40Z","timestamp":1784391580666,"version":"3.55.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial National Science Foundation of China","award":["61572050"],"award-info":[{"award-number":["61572050"]}]},{"name":"Zhejiang Provincial National Science Foundation of China","award":["LY16F020011"],"award-info":[{"award-number":["LY16F020011"]}]},{"name":"Zhejiang Provincial National Science Foundation of China","award":["91538111"],"award-info":[{"award-number":["91538111"]}]},{"name":"Zhejiang Provincial National Science Foundation of China","award":["61620106009"],"award-info":[{"award-number":["61620106009"]}]},{"name":"National 1000 Youth Talents Plan"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1109\/tmm.2017.2766843","type":"journal-article","created":{"date-parts":[[2017,10,26]],"date-time":"2017-10-26T19:47:58Z","timestamp":1509047278000},"page":"1576-1590","source":"Crossref","is-referenced-by-count":375,"title":["Speech Emotion Recognition Using Deep Convolutional Neural Network and Discriminant Temporal Pyramid Matching"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8184-5088","authenticated-orcid":false,"given":"Shiqing","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9053-9314","authenticated-orcid":false,"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4234-6099","authenticated-orcid":false,"given":"Tiejun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2059634"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-013-0192-2"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2058095"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2010.10.001"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-014-1755-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-013-1377-z"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.17"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2392101"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2051872"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref62","author":"florian","year":"2016","journal-title":"Real-Time Speech and Music Classification by Large Audio Feature Space Extraction"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472191"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2016.7527309"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521717"},{"key":"ref65","first-page":"3","article-title":"AVEC 2013-the continuous audio\/visual emotion\n and depression recognition challenge","author":"valstar","year":"0","journal-title":"Proc of International Audio\/Visual Emotion Challenge and Workshop"},{"key":"ref66","first-page":"148","article-title":"The INTERSPEECH 2013 computational\n paralinguistics challenge: Social signals, conflict, emotion, autism","author":"schuller","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/SIU.2015.7130097"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-011-9624-z"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.927665"},{"key":"ref21","first-page":"1517","article-title":"A database of German emotional speech","volume":"5","author":"burkhardt","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2553038"},{"key":"ref23","first-page":"8","article-title":"The eNTERFACE'05 audio-visual emotion\n database","author":"martin","year":"0","journal-title":"Proceedings of the 22nd International Conference on Data Engineering Workshops"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s005210070006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.608022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.03.001"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807412"},{"key":"ref58","first-page":"1818","article-title":"Timing levels in segment-based speech emotion recognition.","author":"schuller","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521436"},{"key":"ref56","author":"fukunaga","year":"2013","journal-title":"Introduction to statistical pattern recognition"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.250598"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44848-9_34"},{"key":"ref52","first-page":"2609","article-title":"Geometric Lp-norm feature pooling for image\n classification","author":"feng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recogn"},{"key":"ref10","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks\n for visual recognition","author":"he","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.04.002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"ref13","first-page":"223","article-title":"Speech emotion recognition\n using deep neural network and extreme learning machine","author":"han","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654984"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref19","first-page":"1237","article-title":"Flexible, high performance convolutional neural networks\n for image classification","volume":"22","author":"ciresan","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9368-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638345"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.14"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.02.005"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2014.10.008"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.08.013"},{"key":"ref42","first-page":"2029","article-title":"Emotional space improves emotion\n recognition","author":"tato","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref41","first-page":"222","article-title":"Emotion recognition in speech signal: Experimental study,\n development, and application","author":"petrushin","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87734-9_52"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367152"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8359225\/08085174.pdf?arnumber=8085174","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:22:40Z","timestamp":1642004560000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8085174\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":70,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2017.2766843","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6]]}}}