{"id":"https://openalex.org/W2899922369","doi":"https://doi.org/10.1109/icassp.2019.8683587","title":"Multimodal One-shot Learning of Speech and Images","display_name":"Multimodal One-shot Learning of Speech and Images","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2899922369","doi":"https://doi.org/10.1109/icassp.2019.8683587","mag":"2899922369"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.03875","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047706306","display_name":"Ryan Eloff","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":true,"raw_author_name":"Ryan Eloff","raw_affiliation_strings":["E&E Engineering, Stellenbosch University, South Africa","StellenBosch University"],"affiliations":[{"raw_affiliation_string":"E&E Engineering, Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"StellenBosch University","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091413322","display_name":"Herman A. Engelbrecht","orcid":"https://orcid.org/0000-0001-8753-8994"},"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 A. Engelbrecht","raw_affiliation_strings":["E&E Engineering, Stellenbosch University, South Africa","StellenBosch University"],"affiliations":[{"raw_affiliation_string":"E&E Engineering, Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"StellenBosch University","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":["E&E Engineering, Stellenbosch University, South Africa","StellenBosch University"],"affiliations":[{"raw_affiliation_string":"E&E Engineering, Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"StellenBosch University","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047706306"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":0.16418009,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40405961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"8623","last_page":"8627"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.984499990940094,"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":0.7414658069610596},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.652728796005249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6445721387863159},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6065781116485596},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5705187320709229},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5590716600418091},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5398049354553223},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5248929262161255},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5197129249572754},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.51945561170578},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5069063305854797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42513507604599},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3463748097419739},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13238218426704407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7414658069610596},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.652728796005249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6445721387863159},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6065781116485596},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5705187320709229},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5590716600418091},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5398049354553223},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5248929262161255},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5197129249572754},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.51945561170578},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5069063305854797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42513507604599},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3463748097419739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13238218426704407},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2019.8683587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.03875","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.03875","pdf_url":"https://arxiv.org/pdf/1811.03875","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2899922369","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.03875","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:scholar.sun.ac.za:10019.1/108185","is_oa":false,"landing_page_url":"http://hdl.handle.net/10019.1/108185","pdf_url":null,"source":{"id":"https://openalex.org/S4306400300","display_name":"SUNScholar (Stellenbosch University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I26092322","host_organization_name":"Stellenbosch University","host_organization_lineage":["https://openalex.org/I26092322"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"doi:10.48550/arxiv.1811.03875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.03875","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.03875","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.03875","pdf_url":"https://arxiv.org/pdf/1811.03875","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2899922369.pdf","grobid_xml":"https://content.openalex.org/works/W2899922369.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1532499126","https://openalex.org/W1975517671","https://openalex.org/W1996194485","https://openalex.org/W2085753829","https://openalex.org/W2091746061","https://openalex.org/W2096733369","https://openalex.org/W2112796928","https://openalex.org/W2114168642","https://openalex.org/W2115733720","https://openalex.org/W2127589108","https://openalex.org/W2127776015","https://openalex.org/W2128160875","https://openalex.org/W2155541015","https://openalex.org/W2157364932","https://openalex.org/W2184188583","https://openalex.org/W2194321275","https://openalex.org/W2220867547","https://openalex.org/W2401823607","https://openalex.org/W2408712009","https://openalex.org/W2415378728","https://openalex.org/W2472819217","https://openalex.org/W2556930864","https://openalex.org/W2557471754","https://openalex.org/W2598634450","https://openalex.org/W2601096423","https://openalex.org/W2601450892","https://openalex.org/W2787501667","https://openalex.org/W2799772357","https://openalex.org/W2884454321","https://openalex.org/W2950133079","https://openalex.org/W2962724383","https://openalex.org/W2962732076","https://openalex.org/W2962862718","https://openalex.org/W2963026686","https://openalex.org/W2963040148","https://openalex.org/W2963341924","https://openalex.org/W2963775347","https://openalex.org/W2964108264","https://openalex.org/W2964222437","https://openalex.org/W3091905774","https://openalex.org/W3099206234","https://openalex.org/W6631190155","https://openalex.org/W6631637103","https://openalex.org/W6633682082","https://openalex.org/W6677180984","https://openalex.org/W6682778277","https://openalex.org/W6686207219","https://openalex.org/W6713057566","https://openalex.org/W6714354170","https://openalex.org/W6717697761","https://openalex.org/W6720057410","https://openalex.org/W6729977899","https://openalex.org/W6734525503","https://openalex.org/W6735236233","https://openalex.org/W6735531217","https://openalex.org/W6735888043","https://openalex.org/W6736057607","https://openalex.org/W6744181227","https://openalex.org/W6747943641","https://openalex.org/W6751201742","https://openalex.org/W6756706075","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W2413342122","https://openalex.org/W2435450765","https://openalex.org/W3135727801","https://openalex.org/W2950276680","https://openalex.org/W3156457440","https://openalex.org/W2974845031","https://openalex.org/W2798836702","https://openalex.org/W3155876088","https://openalex.org/W3124953418","https://openalex.org/W3138829747","https://openalex.org/W2922127534","https://openalex.org/W3197599296","https://openalex.org/W3020764840","https://openalex.org/W3188428738","https://openalex.org/W1966418221","https://openalex.org/W2790040974","https://openalex.org/W3145224227","https://openalex.org/W3011669160","https://openalex.org/W2248968338","https://openalex.org/W3029678209"],"abstract_inverted_index":{"Imagine":[0],"a":[1,27,74,106,133],"robot":[2],"is":[3,25,77,90],"shown":[4,26],"new":[5,28,53],"concepts":[6],"visually":[7],"together":[8],"with":[9],"spoken":[10,110],"tags,":[11],"e.g.":[12],"\"milk\",":[13],"\"eggs\",":[14],"\"butter\".":[15],"After":[16],"seeing":[17],"one":[18,70],"paired":[19,109],"audio-visual":[20],"example":[21,72,82],"per":[22,79],"class,":[23,80],"it":[24,48],"set":[29],"of":[30,33,108,132],"unseen":[31],"instances":[32],"these":[34],"objects,":[35],"and":[36,96,101,111,141],"asked":[37],"to":[38,50,57,91,97,114],"pick":[39],"the":[40,52,58,130],"\"milk\".":[41],"Without":[42],"receiving":[43],"any":[44],"hard":[45],"labels,":[46],"could":[47],"learn":[49],"match":[51],"continuous":[54],"speech":[55,146],"input":[56],"correct":[59],"visual":[60,112],"instance?":[61],"Although":[62],"unimodal":[63],"one-shot":[64,85],"learning":[65],"has":[66],"been":[67],"studied,":[68],"where":[69],"labelled":[71],"in":[73,119,147],"single":[75],"modality":[76],"given":[78],"this":[81,94],"motivates":[83],"multimodal":[84],"learning.":[86],"Our":[87,124],"main":[88],"contribution":[89],"formally":[92],"define":[93],"task,":[95],"propose":[98],"several":[99],"baseline":[100],"advanced":[102],"models.":[103],"We":[104],"use":[105],"dataset":[107],"digits":[113],"specifically":[115],"investigate":[116],"recent":[117],"advances":[118],"Siamese":[120,126],"convolutional":[121],"neural":[122],"networks.":[123],"best":[125],"model":[127,136],"achieves":[128],"twice":[129],"accuracy":[131],"nearest":[134],"neighbour":[135],"using":[137],"pixel-distance":[138],"over":[139,145],"images":[140],"dynamic":[142],"time":[143],"warping":[144],"11-way":[148],"cross-modal":[149],"matching.":[150]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}