{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:57:19Z","timestamp":1781110639347,"version":"3.54.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001863","name":"New Energy and Industrial Technology Development Organization (NEDO), Japan","doi-asserted-by":"publisher","award":["JPNP20006"],"award-info":[{"award-number":["JPNP20006"]}],"id":[{"id":"10.13039\/501100001863","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3225198","type":"journal-article","created":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T19:37:30Z","timestamp":1669664250000},"page":"124396-124407","source":"Crossref","is-referenced-by-count":38,"title":["Evaluating Self-Supervised Speech Representations for Speech Emotion Recognition"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1560-2824","authenticated-orcid":false,"given":"Bagus Tris","family":"Atmaja","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1700-0325","authenticated-orcid":false,"given":"Akira","family":"Sasou","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952655"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1852"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.03.002"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1199"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054317"},{"key":"ref10","article-title":"Language agnostic speech embeddings for emotion classification","author":"nandan","year":"2020","journal-title":"Proc Workshop Self-Supervision Audio Speech (ICML)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.377"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2016.7918977"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICSIGSYS.2019.8811080"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON54134.2021.9707265"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.112.1.155"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref3","first-page":"1","article-title":"DABS: A domain-agnostic benchmark for self-supervised learning","author":"tamkin","year":"2021","journal-title":"Proc NIPS"},{"key":"ref6","article-title":"Prosody, information, and modeling-with emphasis on tonal features of speech","author":"fujisaki","year":"2003","journal-title":"Proc Workshop Spoken Lang Process"},{"key":"ref29","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"dem\u0161ar","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2217"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2070"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383456"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"ref20","first-page":"750","article-title":"A multilingual framework based on pre-training model for speech emotion recognition","author":"zhang","year":"2021","journal-title":"Proc APSIPA Annu Summit Conf"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-349"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09964237.pdf?arnumber=9964237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T17:28:35Z","timestamp":1670261315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9964237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3225198","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}