{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:30:29Z","timestamp":1776882629899,"version":"3.51.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["314602,345365"],"award-info":[{"award-number":["314602,345365"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005781","name":"Kone Foundation","doi-asserted-by":"publisher","award":["L-SCALE"],"award-info":[{"award-number":["L-SCALE"]}],"id":[{"id":"10.13039\/501100005781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,4]]},"DOI":"10.23919\/eusipco58844.2023.10290051","type":"proceedings-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T17:55:44Z","timestamp":1698861344000},"page":"431-435","source":"Crossref","is-referenced-by-count":2,"title":["Simultaneous or Sequential Training? How Speech Representations Cooperate in a Multi-Task Self-Supervised Learning System*"],"prefix":"10.23919","author":[{"given":"Khazar","family":"Khorrami","sequence":"first","affiliation":[{"name":"Tampere University,Unit of Computing Sciences,Tampere,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mar\u00eda Andrea","family":"Cruz Bland\u00f3n","sequence":"additional","affiliation":[{"name":"Tampere University,Unit of Computing Sciences,Tampere,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[{"name":"Tampere University,Unit of Computing Sciences,Tampere,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Okko","family":"R\u00e4s\u00e4nen","sequence":"additional","affiliation":[{"name":"Tampere University,Unit of Computing Sciences,Tampere,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Self-supervised representation learning for speech using visual grounding and masked language modeling","author":"peng","year":"2022","journal-title":"The Self-Supervised Learning for Speech and Audio Processing Workshop at AAAI 2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3206084"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10652"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1006"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-329"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-441"},{"key":"ref10","first-page":"4171","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"kenton","year":"2019","journal-title":"Proceedings of NAACL-HLT"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref2","first-page":"123","article-title":"Can phones, syllables, and words emerge as side-products of cross-situational audiovisual learning?-a computational investigation","volume":"1","author":"khorrami","year":"2021","journal-title":"Lang Dev Res"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12967"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00568-3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1227"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1057"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-1037"}],"event":{"name":"2023 31st European Signal Processing Conference (EUSIPCO)","location":"Helsinki, Finland","start":{"date-parts":[[2023,9,4]]},"end":{"date-parts":[[2023,9,8]]}},"container-title":["2023 31st European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10289698\/10289713\/10290051.pdf?arnumber=10290051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:19:58Z","timestamp":1701112798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10290051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.23919\/eusipco58844.2023.10290051","relation":{},"subject":[],"published":{"date-parts":[[2023,9,4]]}}}