{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T11:15:20Z","timestamp":1784373320225,"version":"3.55.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747095","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7367-7371","source":"Crossref","is-referenced-by-count":153,"title":["Speech Emotion Recognition with Co-Attention Based Multi-Level Acoustic Information"],"prefix":"10.1109","author":[{"given":"Heqing","family":"Zou","sequence":"first","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuke","family":"Si","sequence":"additional","affiliation":[{"name":"Tianjin University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deepu","family":"Rajan","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413635"},{"key":"ref11","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"arXiv preprint arXiv 2006 11116"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-336"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1649"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683163"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1242"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053727"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414286"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413710"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414540"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414654"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414880"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.03.012"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054229"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"18","DOI":"10.25080\/Majora-7b98e3ed-003","article-title":"librosa: Audio and music signal analysis in python","volume":"8","author":"mcfee","year":"2015","journal-title":"Proceedings of the 14th Python in Science Conference"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1852"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747095.pdf?arnumber=9747095","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:25Z","timestamp":1660594285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747095\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747095","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}