{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T22:53:21Z","timestamp":1774306401044,"version":"3.50.1"},"reference-count":29,"publisher":"Cambridge University Press (CUP)","issue":"6","license":[{"start":{"date-parts":[[2020,6,10]],"date-time":"2020-06-10T00:00:00Z","timestamp":1591747200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2021,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>To improve speech emotion recognition, a U-acoustic words emotion dictionary (AWED) features model is proposed based on an AWED. The method models emotional information from acoustic words level in different emotion classes. The top-list words in each emotion are selected to generate the AWED vector. Then, the U-AWED model is constructed by combining utterance-level acoustic features with the AWED features. Support vector machine and convolutional neural network are employed as the classifiers in our experiment. The results show that our proposed method in four tasks of emotion classification all provides significant improvement in unweighted average recall.<\/jats:p>","DOI":"10.1017\/s1351324920000339","type":"journal-article","created":{"date-parts":[[2020,6,10]],"date-time":"2020-06-10T09:05:47Z","timestamp":1591779947000},"page":"747-761","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":7,"title":["Improving speech emotion recognition based on acoustic words emotion dictionary"],"prefix":"10.1017","volume":"27","author":[{"given":"Wang","family":"Wei","sequence":"first","affiliation":[]},{"given":"Xinyi","family":"Cao","sequence":"additional","affiliation":[]},{"given":"He","family":"Li","sequence":"additional","affiliation":[]},{"given":"Lingjie","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Yaqin","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Paul A.","family":"Watters","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2020,6,10]]},"reference":[{"key":"S1351324920000339_ref15","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.11"},{"key":"S1351324920000339_ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388780"},{"key":"S1351324920000339_ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"S1351324920000339_ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.06.004"},{"key":"S1351324920000339_ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-739"},{"key":"S1351324920000339_ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"S1351324920000339_ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"S1351324920000339_ref4","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.99.3.550"},{"key":"S1351324920000339_ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344645"},{"key":"S1351324920000339_ref20","doi-asserted-by":"crossref","unstructured":"Schuller, B. and Rigoll, G. (2006). Timing levels in segment-based speech emotion recognition. In INTERSPEECH 2006, International Conference on Spoken Language Processing (ICSLP), pp. 1818\u20131821.","DOI":"10.21437\/Interspeech.2006-502"},{"key":"S1351324920000339_ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521436"},{"key":"S1351324920000339_ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"S1351324920000339_ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"S1351324920000339_ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"S1351324920000339_ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.04.002"},{"key":"S1351324920000339_ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-103"},{"key":"S1351324920000339_ref29","doi-asserted-by":"crossref","unstructured":"Yang, N. , Muraleedharan, R. , Kohl, J. , Demirkol, I. , Heinzelman, W. and Sturge-Apple, M. 2012. Speech-based emotion classification using multiclass SVM with hybrid kernel and thresholding fusion. In IEEE Workshop on Spoken Language Technology, Miami, FL, pp. 455\u2013460.","DOI":"10.1109\/SLT.2012.6424267"},{"key":"S1351324920000339_ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-917"},{"key":"S1351324920000339_ref13","first-page":"698","article-title":"Recognizing emotions from student speech in tutoring dialogues","volume":"25","author":"Litman","year":"2003","journal-title":"Automatic Speech Recognition and Understanding Workshop"},{"key":"S1351324920000339_ref1","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: interactive emotional dyadic motion capture database","volume":"42","author":"Busso","year":"2008","journal-title":"Language Resources and Evaluation"},{"key":"S1351324920000339_ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2014.6865245"},{"key":"S1351324920000339_ref8","first-page":"50","article-title":"A computational model for the automatic recognition of affect in speech","volume":"28","author":"Fernandez","year":"2004","journal-title":"Thesis Massachusetts Institute of Technology"},{"key":"S1351324920000339_ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"S1351324920000339_ref16","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.40"},{"key":"S1351324920000339_ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.05.003"},{"key":"S1351324920000339_ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288834"},{"key":"S1351324920000339_ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"S1351324920000339_ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"S1351324920000339_ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727636"}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324920000339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T13:28:35Z","timestamp":1635254915000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324920000339\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,10]]},"references-count":29,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["S1351324920000339"],"URL":"https:\/\/doi.org\/10.1017\/s1351324920000339","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"value":"1351-3249","type":"print"},{"value":"1469-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,10]]},"assertion":[{"value":"\u00a9 The Author(s), 2020. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}}]}}