{"id":"https://openalex.org/W2168384584","doi":"https://doi.org/10.1109/icmi.2002.1166977","title":"Towards visually-grounded spoken language acquisition","display_name":"Towards visually-grounded spoken language acquisition","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2168384584","doi":"https://doi.org/10.1109/icmi.2002.1166977","mag":"2168384584"},"language":"en","primary_location":{"id":"doi:10.1109/icmi.2002.1166977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmi.2002.1166977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. Fourth IEEE International Conference on Multimodal Interfaces","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/A5042384857","display_name":"D. \u00d1. Roy","orcid":"https://orcid.org/0000-0002-2688-4241"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"D. Roy","raw_affiliation_strings":["Media Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5042384857"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28467491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"105","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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":0.8080770969390869},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6258776187896729},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6229336261749268},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6042119264602661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5846704840660095},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5648208260536194},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5351978540420532},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.48623576760292053},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.45921987295150757},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4484906792640686},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4345826804637909},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2887907922267914},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09555557370185852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080770969390869},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6258776187896729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6229336261749268},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6042119264602661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5846704840660095},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5648208260536194},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5351978540420532},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.48623576760292053},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.45921987295150757},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4484906792640686},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4345826804637909},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2887907922267914},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09555557370185852},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icmi.2002.1166977","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmi.2002.1166977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. Fourth IEEE International Conference on Multimodal Interfaces","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.7450","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.7450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.media.mit.edu/~dkroy/papers/pdf/roy_2002_c.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W605575788","https://openalex.org/W1804598840","https://openalex.org/W1968211338","https://openalex.org/W1990903069","https://openalex.org/W2027687248","https://openalex.org/W2045342304","https://openalex.org/W2060491487","https://openalex.org/W2107917162","https://openalex.org/W2132921748","https://openalex.org/W2156050092","https://openalex.org/W3128655779","https://openalex.org/W4237938692","https://openalex.org/W6642405941"],"related_works":["https://openalex.org/W2004637830","https://openalex.org/W3034800807","https://openalex.org/W4287758468","https://openalex.org/W2386843486","https://openalex.org/W1538826769","https://openalex.org/W2949597526","https://openalex.org/W4313401079","https://openalex.org/W2739915479","https://openalex.org/W2945848244","https://openalex.org/W4320165414"],"abstract_inverted_index":{"A":[0],"characteristic":[1],"shared":[2],"by":[3],"most":[4],"approaches":[5],"to":[6,43,46,70,76,89],"natural":[7,40],"language":[8,41],"understanding":[9],"and":[10,20,24,72],"generation":[11],"is":[12,49],"the":[13,50],"use":[14],"of":[15,18,29,85,94],"symbolic":[16,30],"representations":[17],"word":[19],"sentence":[21],"meanings.":[22],"Frames":[23],"semantic":[25],"nets":[26],"are":[27,34,83],"examples":[28],"representations.":[31],"Symbolic":[32],"methods":[33],"inappropriate":[35],"for":[36],"applications":[37],"which":[38],"require":[39],"semantics":[42],"be":[44],"linked":[45],"perception,":[47],"as":[48,55],"case":[51],"in":[52],"tasks":[53],"such":[54],"scene":[56],"description":[57],"or":[58],"human-robot":[59],"interaction.":[60],"This":[61],"paper":[62],"presents":[63],"two":[64],"implemented":[65],"systems,":[66],"one":[67,73],"that":[68,74],"learns":[69,75],"generate,":[71],"understand":[77],"visually-grounded":[78],"spoken":[79],"language.":[80],"These":[81],"implementations":[82],"part":[84],"our":[86],"on-going":[87],"effort":[88],"develop":[90],"a":[91],"comprehensive":[92],"model":[93],"perceptually-grounded":[95],"semantics.":[96]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
