{"id":"https://openalex.org/W2601713192","doi":"https://doi.org/10.21437/interspeech.2017-502","title":"Visually Grounded Learning of Keyword Prediction from Untranscribed Speech","display_name":"Visually Grounded Learning of Keyword Prediction from Untranscribed Speech","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2601713192","doi":"https://doi.org/10.21437/interspeech.2017-502","mag":"2601713192"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-502","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/1703.08136","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Herman Kamper","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007445208","display_name":"Shane Settle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shane Settle","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019380351","display_name":"Gregory Shakhnarovich","orcid":"https://orcid.org/0000-0003-4700-9398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gregory Shakhnarovich","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040305929"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9245,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83593483,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9980000257492065,"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":0.9925000071525574,"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":0.832158088684082},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7249303460121155},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6587178707122803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6222318410873413},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5863882303237915},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5502328276634216},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.44938626885414124}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832158088684082},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7249303460121155},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6587178707122803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6222318410873413},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5863882303237915},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5502328276634216},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.44938626885414124}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2017-502","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1703.08136","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.08136","pdf_url":"https://arxiv.org/pdf/1703.08136","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":null,"raw_type":"text"},{"id":"mag:2601713192","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1703.08136.pdf","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":"doi:10.48550/arxiv.1703.08136","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.08136","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:1703.08136","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.08136","pdf_url":"https://arxiv.org/pdf/1703.08136","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G5088725850","display_name":"EAGER: Discovery of Segmental Sub-Word Structure in Speech","funder_award_id":"1433485","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2601713192.pdf","grobid_xml":"https://content.openalex.org/works/W2601713192.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W137009889","https://openalex.org/W170967611","https://openalex.org/W385555557","https://openalex.org/W1486019888","https://openalex.org/W1522301498","https://openalex.org/W1525264136","https://openalex.org/W1686810756","https://openalex.org/W1778492285","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W2010188467","https://openalex.org/W2025482506","https://openalex.org/W2032943813","https://openalex.org/W2033653351","https://openalex.org/W2059168261","https://openalex.org/W2091746061","https://openalex.org/W2108598243","https://openalex.org/W2114347655","https://openalex.org/W2118440833","https://openalex.org/W2126203737","https://openalex.org/W2137010615","https://openalex.org/W2137471889","https://openalex.org/W2171019095","https://openalex.org/W2185175083","https://openalex.org/W2190506272","https://openalex.org/W2220867547","https://openalex.org/W2250874882","https://openalex.org/W2282219577","https://openalex.org/W2295297373","https://openalex.org/W2346964103","https://openalex.org/W2399093011","https://openalex.org/W2466918907","https://openalex.org/W2508907749","https://openalex.org/W2511428026","https://openalex.org/W2531381952","https://openalex.org/W2536305071","https://openalex.org/W2544224704","https://openalex.org/W2556930864","https://openalex.org/W2580178245","https://openalex.org/W2586148577","https://openalex.org/W2593011301","https://openalex.org/W2594392912","https://openalex.org/W2714726990"],"related_works":["https://openalex.org/W2964001192","https://openalex.org/W2903320905","https://openalex.org/W2906407728","https://openalex.org/W3167119498","https://openalex.org/W2964099072","https://openalex.org/W2556930864","https://openalex.org/W2962753610","https://openalex.org/W3114436296","https://openalex.org/W2973135958","https://openalex.org/W3159476814","https://openalex.org/W2963902314","https://openalex.org/W3029191448","https://openalex.org/W2786051023","https://openalex.org/W1980618402","https://openalex.org/W2963288440","https://openalex.org/W2767709712","https://openalex.org/W3041917307","https://openalex.org/W2809767522","https://openalex.org/W2912641852","https://openalex.org/W2971709506"],"abstract_inverted_index":{"During":[0],"language":[1],"acquisition,":[2],"infants":[3],"have":[4,16],"the":[5,74,100,109,137],"benefit":[6],"of":[7,53],"visual":[8,21,82],"cues":[9],"to":[10,18,42,69,84,97,102,115],"ground":[11],"spoken":[12,30,58,125],"language.":[13],"Robots":[14],"similarly":[15],"access":[17],"audio":[19],"and":[20,29,47,91,132,146],"sensors.":[22],"Recent":[23],"work":[24],"has":[25],"shown":[26],"that":[27,108,136],"images":[28,41,54,86],"captions":[31],"can":[32,66],"be":[33,43,67],"mapped":[34],"into":[35],"a":[36,94,124,154],"meaningful":[37],"common":[38],"space,":[39],"allowing":[40],"retrieved":[44],"using":[45],"speech":[46,101,111,131],"vice":[48],"versa.":[49],"In":[50],"this":[51],"setting":[52],"paired":[55],"with":[56,87],"untranscribed":[57],"captions,":[59],"we":[60,77],"consider":[61],"whether":[62],"computer":[63],"vision":[64],"systems":[65],"used":[68],"obtain":[70],"textual":[71,89],"labels":[72],"for":[73],"speech.":[75],"Concretely,":[76],"use":[78],"an":[79,121],"image-to-words":[80],"multi-label":[81],"classifier":[83],"tag":[85],"soft":[88,104],"labels,":[90],"then":[92],"train":[93],"neural":[95],"network":[96],"map":[98],"from":[99],"these":[103],"targets.":[105],"We":[106,134],"show":[107],"resulting":[110],"system":[112],"is":[113],"able":[114],"predict":[116],"which":[117],"words":[118],"occur":[119],"in":[120],"utterance---acting":[122],"as":[123,153],"bag-of-words":[126],"classifier---without":[127],"seeing":[128],"any":[129],"parallel":[130],"text.":[133],"find":[135],"model":[138],"often":[139],"confuses":[140],"semantically":[141],"related":[142],"words,":[143],"e.g.":[144],"\"man\"":[145],"\"person\",":[147],"making":[148],"it":[149],"even":[150],"more":[151],"effective":[152],"semantic":[155],"keyword":[156],"spotter.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}