{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T09:22:22Z","timestamp":1770283342065,"version":"3.49.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053192","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"7174-7178","source":"Crossref","is-referenced-by-count":50,"title":["Speech Emotion Recognition with Local-Global Aware Deep Representation Learning"],"prefix":"10.1109","author":[{"given":"Jiaxing","family":"Liu","sequence":"first","affiliation":[]},{"given":"Zhilei","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Lili","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","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":"ref11","first-page":"1537","article-title":"High-level feature representation using recurrent neural network for speech emotion recognition","author":"lee","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-200"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462219"},{"key":"ref14","first-page":"3856","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"7610","article-title":"Videocapsulenet: A simplified network for action detection","author":"duarte","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2874623"},{"key":"ref17","first-page":"3110","article-title":"Investigating capsule networks with dynamic routing for text classification","author":"min","year":"2018","journal-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1242"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIC.2015.7435630"},{"key":"ref3","first-page":"1252","article-title":"Speech emotion recognition based on mixed mfcc","volume":"249","author":"zhou","year":"2013","journal-title":"Applied Mechanics and Materials"},{"key":"ref6","first-page":"155","article-title":"Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011","volume":"43","author":"iliou","year":"2012","journal-title":"Artificial Intelligence Review"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9172-2"},{"key":"ref8","first-page":"2741","article-title":"Using regional saliency for speech emotion recognition","author":"zakaria","year":"2017","journal-title":"IEEE ICASSP"},{"key":"ref7","first-page":"5200","article-title":"Adieu features? end-to-end speech emotion recognition using a deep convolutional recurrent network","author":"george","year":"2016","journal-title":"IEEE International Conference on Acoustics"},{"key":"ref2","first-page":"937","article-title":"Emotion recognition from human speech using temporal information and deep learning","author":"john","year":"2018","journal-title":"Interspeech 2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-011-9624-z"},{"key":"ref9","first-page":"1611","article-title":"Speech emotion recognition by combining amplitude and phase information using convolutional neural network","author":"wang","year":"2018","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959521"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053192.pdf?arnumber=9053192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:15:48Z","timestamp":1656360948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053192","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}