{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T15:17:00Z","timestamp":1777043820573,"version":"3.51.4"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.23919\/apsipa.2018.8659587","type":"proceedings-article","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T23:11:49Z","timestamp":1552950709000},"page":"1771-1775","source":"Crossref","is-referenced-by-count":107,"title":["Attention Based Fully Convolutional Network for Speech Emotion Recognition"],"prefix":"10.23919","author":[{"given":"Yuanyuan","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[]},{"given":"Zirui","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jianshu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yanhui","family":"Tu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","author":"bahdanau","year":"2014","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.06.017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref14","author":"lin","year":"2017","journal-title":"A structured self-attentive sentence embedding"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref17","first-page":"647","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.5244\/C.30.136","article-title":"Deep sign: hybrid cnn-hmm for continuous sign language recognition","author":"koller","year":"2016","journal-title":"Proceedings of the British Machine Vision Conference 2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5565\/rev\/elcvia.795"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-011-9125-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CSCITA.2014.6839284"},{"key":"ref8","article-title":"Speech emotion recognition using deep neural network and extreme learning machine","author":"han","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"ref2","article-title":"Detecting anger in automated voice portal dialogs","author":"burkhardt","year":"2006","journal-title":"Ninth International Conference on Spoken Language Processing"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.21437\/Interspeech.2017-200","article-title":"Efficient emotion recognition from speech using deep learning on spectrograms","author":"satt","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref22","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"}],"event":{"name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Honolulu, HI, USA","start":{"date-parts":[[2018,11,12]]},"end":{"date-parts":[[2018,11,15]]}},"container-title":["2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8648538\/8659446\/08659587.pdf?arnumber=8659587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T23:31:51Z","timestamp":1598225511000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8659587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":26,"URL":"https:\/\/doi.org\/10.23919\/apsipa.2018.8659587","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}