{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T16:13:24Z","timestamp":1744215204553,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383513","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"365-372","source":"Crossref","is-referenced-by-count":12,"title":["Improving Convolutional Recurrent Neural Networks for Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Patrick","family":"Meyer","sequence":"first","affiliation":[]},{"given":"Ziyi","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Tim","family":"Fingscheidt","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Emotion Recognition From Speech With Recurrent Neural Networks","author":"chernykh","year":"2018"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"312","DOI":"10.21437\/Interspeech.2009-103","article-title":"The INTERSPEECH 2009 Emotion Challenge","author":"schuller","year":"2009","journal-title":"Proc of Interspeech"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1851"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref31","first-page":"1","article-title":"Rethinking Atrous Convolution for Semantic Image Segmentation","author":"chen","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2512598"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.21437\/Interspeech.2005-446","article-title":"A Database of German Emotional Speech","author":"burkhardt","year":"2005","journal-title":"Proc of Interspeech"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683077"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683483"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682154"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2093"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344669"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"ref28","first-page":"2825","article-title":"SciKit-learn: Machine Learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","first-page":"81","article-title":"A New Evaluation Methodology for Speech Emotion Recognition With Confidence Output","author":"meyer","year":"2014","journal-title":"Proc of ITG Conference on Speech Communication"},{"key":"ref27","first-page":"265","article-title":"TensorFlow: A System for Large-Scale Machine Learning","author":"abadi","year":"2016","journal-title":"Proc of OSDI"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s005210070006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref29","first-page":"1","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"Proc of ASRU"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.04.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9368-5"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.608022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019296"},{"key":"ref22","first-page":"1","article-title":"Characterizing Types of Convolution in Deep Convolutional Recurrent Neural Networks for Robust Speech Emotion Recognition","author":"huang","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1832"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054629"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1568"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383513.pdf?arnumber=9383513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T13:16:31Z","timestamp":1671714991000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383513\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383513","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}