{"id":"https://openalex.org/W4319862278","doi":"https://doi.org/10.1109/slt54892.2023.10023079","title":"Towards Visually Prompted Keyword Localisation for Zero-Resource Spoken Languages","display_name":"Towards Visually Prompted Keyword Localisation for Zero-Resource Spoken Languages","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862278","doi":"https://doi.org/10.1109/slt54892.2023.10023079"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023079","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/A5020033363","display_name":"Leanne Nortje","orcid":null},"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":"Leanne Nortje","raw_affiliation_strings":["Stellenbosch University,MediaLab, Electrical & Electronic Engineering,South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University,MediaLab, Electrical & Electronic Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"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,MediaLab, Electrical & Electronic Engineering,South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University,MediaLab, Electrical & Electronic Engineering,South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":0.7283,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78363036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"700","last_page":"707"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8561923503875732},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8180271983146667},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7623122930526733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5686771273612976},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5546662211418152},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5397383570671082},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5085986852645874},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5081470012664795},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.462236225605011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8561923503875732},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8180271983146667},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7623122930526733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5686771273612976},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5546662211418152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5397383570671082},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5085986852645874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5081470012664795},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.462236225605011},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023079","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023079","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":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1987959440","https://openalex.org/W2013596317","https://openalex.org/W2099415988","https://openalex.org/W2101346879","https://openalex.org/W2108598243","https://openalex.org/W2132921748","https://openalex.org/W2194775991","https://openalex.org/W2405666970","https://openalex.org/W2508907749","https://openalex.org/W2896342372","https://openalex.org/W2950133079","https://openalex.org/W2962753610","https://openalex.org/W2962862718","https://openalex.org/W2963902314","https://openalex.org/W2964001192","https://openalex.org/W2964099072","https://openalex.org/W2973135958","https://openalex.org/W2973180715","https://openalex.org/W2995680346","https://openalex.org/W3016087077","https://openalex.org/W3049010983","https://openalex.org/W3095361818","https://openalex.org/W3102219307","https://openalex.org/W3157861865","https://openalex.org/W3198411039","https://openalex.org/W3198749384","https://openalex.org/W3200287550","https://openalex.org/W4224875474","https://openalex.org/W4239171064","https://openalex.org/W4285110637","https://openalex.org/W4297841895","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6728167234","https://openalex.org/W6729977899","https://openalex.org/W6756623301","https://openalex.org/W6770596778","https://openalex.org/W6771812881","https://openalex.org/W6786915337"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4385352507","https://openalex.org/W4389912005","https://openalex.org/W4286904253","https://openalex.org/W2529301793","https://openalex.org/W4307784074","https://openalex.org/W105599799","https://openalex.org/W1483316057"],"abstract_inverted_index":{"Imagine":[0],"being":[1],"able":[2],"to":[3,94],"show":[4,78],"a":[5,7,11,22,42,59,63,72,95,122,144],"system":[6],"visual":[8,96,106,115,136],"depiction":[9],"of":[10,41],"keyword":[12,20,35,52,74,124],"and":[13,30,45,108,141],"finding":[14],"spoken":[15],"utterances":[16],"that":[17,79],"contain":[18],"this":[19,28,114],"from":[21],"zero-resource":[23],"speech":[24],"corpus.":[25],"We":[26,77,91],"formalise":[27],"task":[29],"call":[31],"it":[32],"visually":[33],"prompted":[34],"localisation":[36,149],"(VPKL):":[37],"given":[38],"an":[39,49,87],"image":[40,128],"keyword,":[43],"detect":[44],"predict":[46],"where":[47,100],"in":[48,84,138,148],"utterance":[50],"the":[51,135],"occurs.":[53],"To":[54],"do":[55],"VPKL,":[56],"we":[57,69],"propose":[58],"speech-vision":[60,89],"model":[61,99,132],"with":[62,71,105,110,121],"novel":[64],"localising":[65],"attention":[66],"mechanism":[67],"which":[68],"train":[70],"new":[73,131],"sampling":[75],"scheme.":[76],"these":[80],"innovations":[81],"give":[82],"improvements":[83],"VPKL":[85],"over":[86],"existing":[88],"model.":[90],"also":[92],"compare":[93],"bag-of-words":[97],"(BoW)":[98],"images":[101],"are":[102],"automatically":[103],"tagged":[104],"labels":[107],"paired":[109],"unlabelled":[111],"speech.":[112],"Although":[113],"BoW":[116,137],"can":[117],"be":[118],"queried":[119],"directly":[120],"written":[123],"(while":[125],"our's":[126],"takes":[127],"queries),":[129],"our":[130],"still":[133],"outperforms":[134],"both":[139],"detection":[140],"localisation,":[142],"giving":[143],"16%":[145],"relative":[146],"improvement":[147],"F1.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}