{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T03:37:25Z","timestamp":1783049845470,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":10,"publisher":"ACM","license":[{"start":{"date-parts":[[2014,11,3]],"date-time":"2014-11-03T00:00:00Z","timestamp":1414972800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61272211"],"award-info":[{"award-number":["61272211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61170126"],"award-info":[{"award-number":["61170126"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Six Talent Peaks Foundation of Jiangsu Province","award":["DZXX-027"],"award-info":[{"award-number":["DZXX-027"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2014,11,3]]},"DOI":"10.1145\/2647868.2654984","type":"proceedings-article","created":{"date-parts":[[2014,11,3]],"date-time":"2014-11-03T14:41:51Z","timestamp":1415025711000},"page":"801-804","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":281,"title":["Speech Emotion Recognition Using CNN"],"prefix":"10.1145","author":[{"given":"Zhengwei","family":"Huang","sequence":"first","affiliation":[{"name":"Jiangsu University, Zhenjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Dong","sequence":"additional","affiliation":[{"name":"Wayne State University, Detroit, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qirong","family":"Mao","sequence":"additional","affiliation":[{"name":"Jiangsu University, Zhenjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongzhao","family":"Zhan","sequence":"additional","affiliation":[{"name":"Jiangsu University, Zhenjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2014,11,3]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2051872"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396308"},{"key":"e_1_3_2_1_3_1","volume-title":"Scottsdale","author":"Yu D.","year":"2013","unstructured":"D. Yu , M. L. Seltzer , J. Li , J. T. Huang , and S. Frank , \" Feature learning in deep neural networks - studies on speech recognition tasks,\" in ICLR , Scottsdale , Arizona, USA , May 2013 . D. Yu, M. L. Seltzer, J. Li, J. T. Huang, and S. Frank, \"Feature learning in deep neural networks - studies on speech recognition tasks,\" in ICLR, Scottsdale, Arizona, USA, May 2013."},{"key":"e_1_3_2_1_4_1","volume-title":"British Columbia","author":"Kim Y.","year":"2013","unstructured":"Y. Kim and H. L. et. al., \"Deep learning for robust feature generation in audio-visual emotion recognition,\" Vancouver , British Columbia , Canada , 2013 . Y. Kim and H. L. et. al., \"Deep learning for robust feature generation in audio-visual emotion recognition,\" Vancouver, British Columbia, Canada, 2013."},{"key":"e_1_3_2_1_5_1","volume-title":"Czech Republic","author":"Le D.","year":"2013","unstructured":"D. Le and E. M. Provost , \" Emotion recognition from spontaneous speech using hidden markov models with deep belief networks,\" Olomouc , Czech Republic , 2013 . D. Le and E. M. Provost, \"Emotion recognition from spontaneous speech using hidden markov models with deep belief networks,\" Olomouc, Czech Republic, 2013."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396383"},{"key":"e_1_3_2_1_7_1","first-page":"53","volume-title":"UK","author":"Haq S.","year":"2009","unstructured":"S. Haq , P. Jackson , and J. Edge , \" Speaker-dependent audio-visual emotion recognition,\" in AVSP, Norwich , UK , Sept. 2009 , pp. 53 -- 58 . S. Haq, P. Jackson, and J. Edge, \"Speaker-dependent audio-visual emotion recognition,\" in AVSP, Norwich,UK, Sept. 2009, pp. 53--58."},{"key":"e_1_3_2_1_8_1","first-page":"1517","article-title":"A database of german emotional speech,\" in Interspeech, Lissabon","volume":"2005","author":"Burkhardt F.","unstructured":"F. Burkhardt , A. Paeschke , M. Rolfes , and W. Sendlmeier , \" A database of german emotional speech,\" in Interspeech, Lissabon , Portugal, Sept . 2005 , pp. 1517 -- 1520 . F. Burkhardt, A. Paeschke, M. Rolfes, and W. Sendlmeier, \"A database of german emotional speech,\" in Interspeech, Lissabon, Portugal, Sept.2005, pp. 1517--1520.","journal-title":"Portugal, Sept"},{"key":"e_1_3_2_1_9_1","volume-title":"Documentation of the Danish emotional speech database DES. {Online}.Available: http:\/\/cpk.auc.dk\/tb\/speech\/emotions\/","author":"Engberg I.","year":"1996","unstructured":"I. Engberg and A. Hansen . ( 1996 ) Documentation of the Danish emotional speech database DES. {Online}.Available: http:\/\/cpk.auc.dk\/tb\/speech\/emotions\/ I. Engberg and A. Hansen. (1996) Documentation of the Danish emotional speech database DES. {Online}.Available: http:\/\/cpk.auc.dk\/tb\/speech\/emotions\/"},{"key":"e_1_3_2_1_10_1","first-page":"61","volume-title":"Shanghai","author":"Fu L.","year":"2008","unstructured":"L. Fu , X. Mao , and L. Chen , \" Speaker independent emotion recognition based on SVM\/HMMs fusion system,\" in ICALIP , Shanghai , China , July 2008 , pp. 61 -- 65 . L. Fu, X. Mao, and L. Chen, \"Speaker independent emotion recognition based on SVM\/HMMs fusion system,\" in ICALIP, Shanghai, China, July 2008, pp. 61--65."}],"event":{"name":"MM '14: 2014 ACM Multimedia Conference","location":"Orlando Florida USA","acronym":"MM '14","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 22nd ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2647868.2654984","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2647868.2654984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:13:20Z","timestamp":1750227200000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2647868.2654984"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,11,3]]},"references-count":10,"alternative-id":["10.1145\/2647868.2654984","10.1145\/2647868"],"URL":"https:\/\/doi.org\/10.1145\/2647868.2654984","relation":{},"subject":[],"published":{"date-parts":[[2014,11,3]]},"assertion":[{"value":"2014-11-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}