{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:35:10Z","timestamp":1769632510186,"version":"3.49.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3393772","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T17:56:58Z","timestamp":1714067818000},"page":"2544-2554","source":"Crossref","is-referenced-by-count":3,"title":["Visually Grounded Few-Shot Word Learning in Low-Resource Settings"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0021-3968","authenticated-orcid":false,"given":"Leanne","family":"Nortje","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4354-4393","authenticated-orcid":false,"given":"Dan","family":"Onea\u0163\u0103","sequence":"additional","affiliation":[{"name":"University Politehnica of Bucharest, Bucharest, Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2980-3475","authenticated-orcid":false,"given":"Herman","family":"Kamper","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.07.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/\/0033-295X.94.2.115"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0987-94"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(00)01467-4"},{"key":"ref5","first-page":"803","article-title":"One-shot learning of generative speech concepts","volume-title":"Proc. Annu. Meeting Cogn. Sci. Soc.","author":"Lake","year":"2014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1037\/a0039702"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683587"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-87"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-49"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683275"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-435"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12967"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-022-10059-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2044"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096882"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10966"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023079"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023089"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-668"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683639"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-82"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462002"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2364"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-50"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2836(70)90057-4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462396"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref37","first-page":"1866","article-title":"Unsupervised learning of spoken language with visual context","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Harwath","year":"2016"},{"key":"ref38","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref39","first-page":"139","article-title":"Collecting image annotations using amazons mechanical turk","volume-title":"NAACL HLT Workshop","author":"Rashtchian","year":"2010"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2872106"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248100"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3060805"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383594"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10508479.pdf?arnumber=10508479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T04:43:34Z","timestamp":1715057014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3393772","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}