{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T03:50:59Z","timestamp":1777002659452,"version":"3.51.4"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413710","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6314-6318","source":"Crossref","is-referenced-by-count":15,"title":["Domain-Adversarial Autoencoder with Attention Based Feature Level Fusion for Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Yuan","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"JiaXing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","volume":"2013","author":"lu","year":"2013","journal-title":"InterSpeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2324759"},{"key":"ref12","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.905145"},{"key":"ref14","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","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":"InterSpeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref17","article-title":"Surrey audio-visual expressed emotion (savee) database","author":"jackson","year":"2014"},{"key":"ref18","article-title":"A database of german emotional speech","author":"burkhardt","year":"2005","journal-title":"Ninth European Conference on Speech Communication and Technology"},{"key":"ref19","article-title":"The emotional voices database: Towards controlling the emotion dimension in voice generation systems","author":"adigwe","year":"2018","journal-title":"arXiv preprint arXiv 1806 09514"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1132"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1520"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682541"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.8"},{"key":"ref21","first-page":"384","article-title":"Learning a parametric embedding by preserving local structure","author":"van der maaten","year":"2009","journal-title":"Artificial Intelligence and Statistics"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413710.pdf?arnumber=9413710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:57Z","timestamp":1652197257000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413710","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}