{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T06:44:14Z","timestamp":1764225854573},"reference-count":45,"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\/slt54892.2023.10023089","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"731-738","source":"Crossref","is-referenced-by-count":3,"title":["YFACC: A Yor\u00f9b\u00e1 Speech\u2013Image Dataset for Cross-Lingual Keyword Localisation Through Visual Grounding"],"prefix":"10.1109","author":[{"given":"Kayode","family":"Olaleye","sequence":"first","affiliation":[{"name":"Stellenbosch University,South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Oneata","sequence":"additional","affiliation":[{"name":"University Politehnica of Bucharest,Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herman","family":"Kamper","sequence":"additional","affiliation":[{"name":"Stellenbosch University,South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/slt.2010.5700813"},{"article-title":"Learning words from images and speech","volume-title":"NeurIPS Workshop Learn","author":"Synnaeve","key":"ref2"},{"article-title":"Deep multimodal semantic em-beddings for speech and images","volume-title":"Proc. ASRU","author":"Harwath","key":"ref3"},{"article-title":"Unsupervised learning of spoken language with visual context","volume-title":"Proc. NeurIPS","author":"Harwath","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462396"},{"article-title":"Multi-modal one-shot learning of speech and images","volume-title":"Proc. ICASSP","author":"Eloff","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682666"},{"article-title":"Learning hierar-chical discrete linguistic units from visually-grounded speech","volume-title":"Proc. ICLR","author":"Harwath","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-87"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053428"},{"volume-title":"Lagos-NWU Yoruba speech corpus","year":"2015","author":"van Niekerk","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1096"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10850"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-152"},{"article-title":"Collecting image annotations using Amazons Mechanical Turk","volume-title":"NAACL HLT Workshop","author":"Rashtchian","key":"ref17"},{"article-title":"Framing image description as a ranking task: Data, models and evaluation metrics (extended abstract)","volume-title":"Proc. IJCAI","author":"Hodosh","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912049"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-53"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-435"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3180220"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-502"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-1057"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2018.2872106"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3051"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/278459.258544"},{"key":"ref29","article-title":"Cross-language infor-mation retrieval","author":"Oard","year":"1998","journal-title":"ARIST"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1109"},{"article-title":"To-wards speech-to-text translation without speech recognition","volume-title":"Proc. EACL","author":"Bansal","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref34","article-title":"Speak and unspeak with PRAAT","author":"Boersma","year":"2001","journal-title":"Glot Int."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"article-title":"Image2speech: Automatically generating audio descriptions of images","volume-title":"Proc. IC-NLSP","author":"Hasegawa-Johnson","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987417"},{"volume-title":"Notes on the construction of the Yoruba language","year":"1879","author":"Wood","key":"ref38"},{"key":"ref39","article-title":"Im-proving Yoruba diacritic restoration","author":"Orife","year":"2020","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.482"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054678"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"ar Xiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma","key":"ref45"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","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\/10023089.pdf?arnumber=10023089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:49:46Z","timestamp":1707806986000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023089\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023089","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}