{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T19:08:23Z","timestamp":1771528103783,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023079","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"700-707","source":"Crossref","is-referenced-by-count":5,"title":["Towards Visually Prompted Keyword Localisation for Zero-Resource Spoken Languages"],"prefix":"10.1109","author":[{"given":"Leanne","family":"Nortje","sequence":"first","affiliation":[{"name":"Stellenbosch University,MediaLab, Electrical & Electronic Engineering,South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herman","family":"Kamper","sequence":"additional","affiliation":[{"name":"Stellenbosch University,MediaLab, Electrical & Electronic Engineering,South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12967"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"},{"key":"ref4","article-title":"Unsupervised learning of spoken language with visual context","volume-title":"Proc. NIPS","author":"Harwath"},{"key":"ref5","article-title":"Vision as an In-terlingua: Learning multilingual semantic embeddings of untranscribed speech","volume-title":"Proc. ICASSP","author":"Harwath"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10652"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3051"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-435"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054678"},{"key":"ref11","article-title":"Towards localisation of keywords in speech using weak supervision","volume-title":"Proc. NeurIPS-SAS","author":"Olaleye"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3180220"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0965(83)90085-1"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1037\/e412952005-009","volume-title":"The Language Instinct","author":"Pinker","year":"1994"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/1131427"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2003.811618"},{"key":"ref17","article-title":"ACORNS - to-wards computational modeling of communication and recognition skills","volume-title":"Proc. ICCI","author":"Boves"},{"key":"ref18","article-title":"From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning","volume-title":"Proc. COLING","author":"Gelderloos"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1523"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0987-94"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2006.1660179"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-69"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/29.103088"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-502"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-53"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-968"},{"key":"ref29","article-title":"Libri-light: A Bench-mark for ASR with limited or no supervision","volume-title":"Proc. ICASSP","author":"Kahn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref31","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref33","article-title":"Learning hier-archical discrete linguistic units from visually-grounded speech","author":"Harwath","year":"2020","journal-title":"arXv preprint"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2872106"},{"key":"ref36","article-title":"Multi-modal one-shot learning of speech and images","volume-title":"Proc. ICASSP","author":"Eloff"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10966"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-87"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-49"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023079.pdf?arnumber=10023079","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:35:31Z","timestamp":1707813331000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023079\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023079","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}