{"id":"https://openalex.org/W4306317873","doi":"https://doi.org/10.1007/s12559-022-10059-7","title":"Modelling Human Word Learning and Recognition Using Visually Grounded Speech","display_name":"Modelling Human Word Learning and Recognition Using Visually Grounded Speech","publication_year":2022,"publication_date":"2022-10-15","ids":{"openalex":"https://openalex.org/W4306317873","doi":"https://doi.org/10.1007/s12559-022-10059-7"},"language":"en","primary_location":{"id":"doi:10.1007/s12559-022-10059-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-022-10059-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-022-10059-7.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s12559-022-10059-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104830677","display_name":"Danny Merkx","orcid":null},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]},{"id":"https://openalex.org/I4210106878","display_name":"Korps Landelijke Politiediensten","ror":"https://ror.org/01trfzy92","country_code":"NL","type":"government","lineage":["https://openalex.org/I4210101771","https://openalex.org/I4210106878","https://openalex.org/I4210140876"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Danny Merkx","raw_affiliation_strings":["Centre for Language Studies, Radboud University, Nijmegen, The Netherlands","Department of Intelligent Systems, Delft University of Technology, Delft, The Netherlands","Dutch National Police, The Hague, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-5829-5214","affiliations":[{"raw_affiliation_string":"Centre for Language Studies, Radboud University, Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Department of Intelligent Systems, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Dutch National Police, The Hague, The Netherlands","institution_ids":["https://openalex.org/I4210106878"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048906210","display_name":"Sebastiaan Scholten","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sebastiaan Scholten","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076704114","display_name":"Stefan L. Frank","orcid":"https://orcid.org/0000-0002-7026-711X"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Stefan L. Frank","raw_affiliation_strings":["Centre for Language Studies, Radboud University, Nijmegen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Language Studies, Radboud University, Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091677603","display_name":"Mirjam Ernestus","orcid":"https://orcid.org/0000-0002-1853-0750"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mirjam Ernestus","raw_affiliation_strings":["Centre for Language Studies, Radboud University, Nijmegen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Language Studies, Radboud University, Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104830677"],"corresponding_institution_ids":["https://openalex.org/I145872427","https://openalex.org/I4210106878","https://openalex.org/I98358874"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2790},"fwci":0.782,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72140874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"15","issue":"1","first_page":"272","last_page":"288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9979000091552734,"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/T12031","display_name":"Speech and dialogue systems","score":0.9939000010490417,"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":0.7154303789138794},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.5671976804733276},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5593584179878235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5511958003044128},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5359241962432861},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4184425473213196},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17593663930892944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7154303789138794},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.5671976804733276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5593584179878235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5511958003044128},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5359241962432861},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4184425473213196},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17593663930892944},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s12559-022-10059-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-022-10059-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-022-10059-7.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/302256","is_oa":true,"landing_page_url":"https://hdl.handle.net/2066/302256","pdf_url":"https://repository.ubn.ru.nl//bitstream/handle/2066/302256/302256.pdf","source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article / Letter to editor"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/288740","is_oa":false,"landing_page_url":"https://repository.ubn.ru.nl/handle/2066/288740","pdf_url":null,"source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cognitive Computation","raw_type":"Article / Letter to editor"},{"id":"pmh:oai:tudelft.nl:uuid:2bcc937d-50c7-4e89-905c-7c2deca064e1","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:2bcc937d-50c7-4e89-905c-7c2deca064e1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1007/s12559-022-10059-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12559-022-10059-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12559-022-10059-7.pdf","source":{"id":"https://openalex.org/S133078663","display_name":"Cognitive Computation","issn_l":"1866-9956","issn":["1866-9956","1866-9964"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Computation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2084304408","display_name":null,"funder_award_id":"024.001.006","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306317873.pdf","grobid_xml":"https://content.openalex.org/works/W4306317873.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1497970776","https://openalex.org/W1514535095","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1957706851","https://openalex.org/W1965349238","https://openalex.org/W1979633237","https://openalex.org/W1991739681","https://openalex.org/W2001622426","https://openalex.org/W2006497363","https://openalex.org/W2006586657","https://openalex.org/W2010418158","https://openalex.org/W2014371677","https://openalex.org/W2017558771","https://openalex.org/W2026992087","https://openalex.org/W2086335849","https://openalex.org/W2108598243","https://openalex.org/W2115213193","https://openalex.org/W2127802090","https://openalex.org/W2130368366","https://openalex.org/W2135280482","https://openalex.org/W2165351142","https://openalex.org/W2194775991","https://openalex.org/W2236615147","https://openalex.org/W2321216766","https://openalex.org/W2415378728","https://openalex.org/W2586148577","https://openalex.org/W2752796333","https://openalex.org/W2753311918","https://openalex.org/W2786358356","https://openalex.org/W2923959898","https://openalex.org/W2950133079","https://openalex.org/W2962862718","https://openalex.org/W2962866381","https://openalex.org/W2963849887","https://openalex.org/W2963902314","https://openalex.org/W2964001192","https://openalex.org/W2964054038","https://openalex.org/W2964099072","https://openalex.org/W2971709506","https://openalex.org/W2972892814","https://openalex.org/W2973180715","https://openalex.org/W2989358187","https://openalex.org/W3005578234","https://openalex.org/W3035750922","https://openalex.org/W3094626712","https://openalex.org/W3095361818","https://openalex.org/W3099041253","https://openalex.org/W3099142230","https://openalex.org/W3100113836","https://openalex.org/W3102219307","https://openalex.org/W3102887392","https://openalex.org/W3120008787","https://openalex.org/W3158565912","https://openalex.org/W3159476814","https://openalex.org/W3198266945","https://openalex.org/W4211055288","https://openalex.org/W4213145363","https://openalex.org/W4281396182"],"related_works":["https://openalex.org/W2519669014","https://openalex.org/W3212726904","https://openalex.org/W1500610678","https://openalex.org/W2255389974","https://openalex.org/W1990771804","https://openalex.org/W748042587","https://openalex.org/W1569283511","https://openalex.org/W2919547998","https://openalex.org/W3204019825","https://openalex.org/W2296205523"],"abstract_inverted_index":{"Abstract":[0],"Many":[1],"computational":[2],"models":[3,21,44,72],"of":[4,11,78,92,101,151],"speech":[5,25,43,48,71,94,129,200],"recognition":[6,105,119,150,181],"assume":[7],"that":[8,19,68,156,180,207,223],"the":[9,76,81,98,109,144,147,157,188,224,231],"set":[10],"target":[12,232],"words":[13,79,233],"is":[14,120,159,182,210,227],"already":[15],"given.":[16],"This":[17],"implies":[18],"these":[20],"learn":[22,45,73],"to":[23,46,74,115,161,169,229],"recognise":[24,47,75,162,230],"in":[26,80,127,146,164,198,212],"a":[27,87,90,112,137],"biologically":[28],"unrealistic":[29],"manner,":[30],"i.e.":[31],"with":[32],"prior":[33,50],"lexical":[34,51],"knowledge":[35,52],"and":[36,59,103,149,166,174,191,214],"explicit":[37],"supervision.":[38],"In":[39],"contrast,":[40],"visually":[41,69],"grounded":[42,70],"without":[49],"by":[53,108,122,184],"exploiting":[54],"statistical":[55],"dependencies":[56],"between":[57,172],"spoken":[58],"visual":[60],"input.":[61],"While":[62],"it":[63],"has":[64],"previously":[65],"been":[66],"shown":[67],"presence":[77],"input,":[82],"we":[83,203],"explicitly":[84],"investigate":[85,97,133],"such":[86],"model":[88,91,110,145,158,226],"as":[89,106],"human":[93,128,199],"recognition.":[95],"We":[96,131,177],"time":[99],"course":[100],"noun":[102],"verb":[104],"simulated":[107],"using":[111],"gating":[113,219],"paradigm":[114],"test":[116],"whether":[117,134],"its":[118],"affected":[121],"well-known":[123],"word":[124,185,195],"competition":[125,186,196],"effects":[126,197],"processing.":[130],"furthermore":[132],"vector":[135,208],"quantisation,":[136],"technique":[138],"for":[139],"discrete":[140],"representation":[141],"learning,":[142],"aids":[143],"discovery":[148],"words.":[152],"Our":[153],"experiments":[154],"show":[155,222],"able":[160,228],"nouns":[163],"isolation":[165],"even":[167],"learns":[168],"properly":[170],"differentiate":[171],"plural":[173],"singular":[175],"nouns.":[176],"also":[178],"find":[179,204],"influenced":[183],"from":[187],"word-initial":[189],"cohort":[190],"neighbourhood":[192],"density,":[193],"mirroring":[194],"comprehension.":[201],"Lastly,":[202],"no":[205],"evidence":[206],"quantisation":[209],"helpful":[211],"discovering":[213],"recognising":[215],"words,":[216],"though":[217],"our":[218],"experiment":[220],"does":[221],"LSTM-VQ":[225],"earlier.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2022-10-16T00:00:00"}