{"id":"https://openalex.org/W4319862234","doi":"https://doi.org/10.1109/slt54892.2023.10023089","title":"YFACC: A Yor\u00f9b\u00e1 Speech\u2013Image Dataset for Cross-Lingual Keyword Localisation Through Visual Grounding","display_name":"YFACC: A Yor\u00f9b\u00e1 Speech\u2013Image Dataset for Cross-Lingual Keyword Localisation Through Visual Grounding","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862234","doi":"https://doi.org/10.1109/slt54892.2023.10023089"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023089","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081862617","display_name":"Kayode Olaleye","orcid":"https://orcid.org/0000-0002-2622-7305"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Kayode Olaleye","raw_affiliation_strings":["Stellenbosch University,South Africa","Stellenbosch University, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University,South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013389452","display_name":"Dan Onea\u0163\u0103","orcid":"https://orcid.org/0000-0003-4354-4393"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Dan Oneata","raw_affiliation_strings":["University Politehnica of Bucharest,Romania","University Politehnica of Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"University Politehnica of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["Stellenbosch University,South Africa","Stellenbosch University, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University,South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3641,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63258086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"731","last_page":"738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/yoruba","display_name":"Yoruba","score":0.9391732811927795},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8235056400299072},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6439446210861206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5365239381790161},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5227373242378235},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4926484227180481},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43579670786857605},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1655592918395996}],"concepts":[{"id":"https://openalex.org/C2777568999","wikidata":"https://www.wikidata.org/wiki/Q34311","display_name":"Yoruba","level":2,"score":0.9391732811927795},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235056400299072},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6439446210861206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5365239381790161},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5227373242378235},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4926484227180481},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43579670786857605},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1655592918395996},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023089","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W652419217","https://openalex.org/W1543039027","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2104247845","https://openalex.org/W2418300416","https://openalex.org/W2466918907","https://openalex.org/W2586148577","https://openalex.org/W2605131327","https://openalex.org/W2927673779","https://openalex.org/W2936774411","https://openalex.org/W2950133079","https://openalex.org/W2962753610","https://openalex.org/W2963330681","https://openalex.org/W2963902314","https://openalex.org/W2963909453","https://openalex.org/W2964001192","https://openalex.org/W2964099072","https://openalex.org/W2973135958","https://openalex.org/W3013173896","https://openalex.org/W3015215494","https://openalex.org/W3015300171","https://openalex.org/W3016087077","https://openalex.org/W3049010983","https://openalex.org/W3092791109","https://openalex.org/W3099142230","https://openalex.org/W3102003804","https://openalex.org/W3102219307","https://openalex.org/W3125533710","https://openalex.org/W3198411039","https://openalex.org/W4285045129","https://openalex.org/W4285110637","https://openalex.org/W4285155368","https://openalex.org/W4296068421","https://openalex.org/W4300558631","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6677994088","https://openalex.org/W6680628865","https://openalex.org/W6697284302","https://openalex.org/W6729977899","https://openalex.org/W6756623301","https://openalex.org/W6770596778","https://openalex.org/W6775275162","https://openalex.org/W6807079506","https://openalex.org/W6864391120","https://openalex.org/W7009000405"],"related_works":["https://openalex.org/W2611614995","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W1552159754","https://openalex.org/W2148757832","https://openalex.org/W2368779261","https://openalex.org/W2374918184","https://openalex.org/W2108273745","https://openalex.org/W2166143226","https://openalex.org/W4285412918"],"abstract_inverted_index":{"Visually":[0],"grounded":[1],"speech":[2,21],"(VGS)":[3],"models":[4,15,148],"are":[5,42,87],"trained":[6,128],"on":[7,129],"images":[8,70,86],"paired":[9,95],"with":[10,90,96],"unlabelled":[11],"spoken":[12,76],"captions.":[13],"Such":[14],"could":[16],"be":[17],"used":[18],"to":[19,29,52,125],"build":[20],"systems":[22,127],"in":[23,43,71,77,112,143],"settings":[24],"where":[25,85],"it":[26],"is":[27,108],"impossible":[28],"get":[30],"labelled":[31],"data,":[32],"e.g.":[33],"for":[34,67,149],"documenting":[35],"unwritten":[36],"languages.":[37,48,152],"However,":[38],"most":[39],"VGS":[40,83,147],"studies":[41],"English":[44,91,106,126],"or":[45],"other":[46],"high-resource":[47],"This":[49,99],"paper":[50],"attempts":[51],"address":[53],"this":[54,137],"shortcoming.":[55],"We":[56,79,134],"collect":[57],"and":[58,94,110,131],"release":[59],"a":[60,104],"new":[61,138],"single-speaker":[62],"dataset":[63,139],"of":[64,119,146],"audio":[65],"captions":[66],"6k":[68],"Flickr":[69],"Yoruba=-a":[72],"real":[73,150],"low-resource":[74,151],"language":[75],"Nigeria.":[78],"train":[80],"an":[81],"attention-based":[82],"model":[84],"automatically":[88],"tagged":[89],"visual":[92],"labels":[93],"Yoruba":[97,113],"utterances.":[98],"enables":[100],"cross-lingual":[101],"keyword":[102],"localisation:":[103],"written":[105],"query":[107],"detected":[109],"located":[111],"speech.":[114],"To":[115],"quantify":[116],"the":[117,120,144],"effect":[118],"smaller":[121],"dataset,":[122],"we":[123],"compare":[124],"similar":[130],"more":[132],"data.":[133],"hope":[135],"that":[136],"will":[140],"stimulate":[141],"research":[142],"use":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}