{"id":"https://openalex.org/W2107917162","doi":"https://doi.org/10.1016/s0364-0213(01)00061-1","title":"Learning words from sights and sounds: a computational model","display_name":"Learning words from sights and sounds: a computational model","publication_year":2002,"publication_date":"2002-02-01","ids":{"openalex":"https://openalex.org/W2107917162","doi":"https://doi.org/10.1016/s0364-0213(01)00061-1","mag":"2107917162"},"language":"en","primary_location":{"id":"doi:10.1016/s0364-0213(01)00061-1","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0364-0213(01)00061-1","pdf_url":null,"source":{"id":"https://openalex.org/S78735424","display_name":"Cognitive Science","issn_l":"0364-0213","issn":["0364-0213","1551-6709"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Science","raw_type":"journal-article"},"type":"article","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/A5004281470","display_name":"Deb Roy","orcid":"https://orcid.org/0000-0002-2780-4768"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"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":["MIT Media Laboratory, 20 Ames Street, Room E15-488, Cambridge, MA 01242, USA","MIT Media Laboratory, 20 Ames Street, Room E15\u2013488, Cambridge, MA 01242, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Media Laboratory, 20 Ames Street, Room E15-488, Cambridge, MA 01242, USA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"MIT Media Laboratory, 20 Ames Street, Room E15\u2013488, Cambridge, MA 01242, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004281470"],"corresponding_institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"],"apc_list":{"value":3810,"currency":"USD","value_usd":3810},"apc_paid":null,"fwci":48.6472,"has_fulltext":false,"cited_by_count":483,"citation_normalized_percentile":{"value":0.99862813,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"26","issue":"1","first_page":"113","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.995199978351593,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.995199978351593,"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/T10730","display_name":"Language Development and Disorders","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9850999712944031,"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":0.8027604818344116},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5884020924568176},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5871214866638184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5867193937301636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5184214115142822},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47101032733917236},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.4657626450061798},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4579838812351227},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41872918605804443},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4158147871494293},{"id":"https://openalex.org/keywords/sight","display_name":"Sight","score":0.4124016761779785},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3306894302368164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027604818344116},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5884020924568176},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5871214866638184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867193937301636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5184214115142822},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47101032733917236},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.4657626450061798},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4579838812351227},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41872918605804443},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4158147871494293},{"id":"https://openalex.org/C1517167","wikidata":"https://www.wikidata.org/wiki/Q1134322","display_name":"Sight","level":2,"score":0.4124016761779785},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3306894302368164},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1016/s0364-0213(01)00061-1","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0364-0213(01)00061-1","pdf_url":null,"source":{"id":"https://openalex.org/S78735424","display_name":"Cognitive Science","issn_l":"0364-0213","issn":["0364-0213","1551-6709"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Science","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.131.1156","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.131.1156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/~kuipers/readings/Roy-cogsci-02.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.15.3577","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.15.3577","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/cogsci_v2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.20.4858","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.4858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.media.mit.edu/cogmac/cogsci_2002.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.34.9295","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.34.9295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vismod.www.media.mit.edu/~dkroy/papers/pdf/phd_thesis.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.61.2924","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.2924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.media.mit.edu/cogmac/publications/cogsci_print.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.8985","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.8985","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_pentland_2002.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W170174517","https://openalex.org/W285471286","https://openalex.org/W322227076","https://openalex.org/W1499050190","https://openalex.org/W1534064252","https://openalex.org/W1535702289","https://openalex.org/W1554663460","https://openalex.org/W1628323995","https://openalex.org/W1855262058","https://openalex.org/W1942647574","https://openalex.org/W1971771135","https://openalex.org/W1980491396","https://openalex.org/W1980862600","https://openalex.org/W1982374456","https://openalex.org/W1992119553","https://openalex.org/W2022378810","https://openalex.org/W2029948425","https://openalex.org/W2045830397","https://openalex.org/W2054658115","https://openalex.org/W2060491487","https://openalex.org/W2065114842","https://openalex.org/W2067242602","https://openalex.org/W2073022807","https://openalex.org/W2074546930","https://openalex.org/W2074855560","https://openalex.org/W2090072485","https://openalex.org/W2099111195","https://openalex.org/W2110871230","https://openalex.org/W2112166433","https://openalex.org/W2123758925","https://openalex.org/W2124973255","https://openalex.org/W2125838338","https://openalex.org/W2126493631","https://openalex.org/W2135884851","https://openalex.org/W2137075158","https://openalex.org/W2140661818","https://openalex.org/W2141622386","https://openalex.org/W2149492821","https://openalex.org/W2162922114","https://openalex.org/W2165470078","https://openalex.org/W2333916262","https://openalex.org/W2509276541","https://openalex.org/W2566861030","https://openalex.org/W2882319491","https://openalex.org/W2952343510","https://openalex.org/W3036063182","https://openalex.org/W3128655779","https://openalex.org/W4237938692","https://openalex.org/W4238354054","https://openalex.org/W4245122798","https://openalex.org/W4250234291","https://openalex.org/W4253573210","https://openalex.org/W4388297464"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W3214178347","https://openalex.org/W2382615723","https://openalex.org/W2353119552","https://openalex.org/W2364379655","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2808673637","https://openalex.org/W2623658258"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,20],"implemented":[4,41],"computational":[5],"model":[6,25,38,58],"of":[7,76,84],"word":[8,63],"acquisition":[9],"which":[10,99],"learns":[11],"directly":[12],"from":[13,68,88],"raw":[14,102],"multimodal":[15],"sensory":[16,89],"input.":[17],"Set":[18],"in":[19,42],"information":[21],"theoretic":[22],"framework,":[23],"the":[24,57,82,106],"acquires":[26],"a":[27,43],"lexicon":[28],"by":[29],"finding":[30],"and":[31,51,65,92],"statistically":[32],"modeling":[33],"consistent":[34],"cross-modal":[35],"structure.":[36],"The":[37],"has":[39],"been":[40],"system":[44],"using":[45,85],"novel":[46],"speech":[47,61,71],"processing,":[48],"computer":[49],"vision,":[50],"machine":[52,93],"learning":[53,94],"algorithms.":[54],"In":[55],"evaluations":[56],"successfully":[59],"performed":[60],"segmentation,":[62],"discovery":[64],"visual":[66],"categorization":[67],"spontaneous":[69],"infant-directed":[70],"paired":[72],"with":[73],"video":[74],"images":[75],"single":[77],"objects.":[78],"These":[79],"results":[80],"demonstrate":[81],"possibility":[83],"state-of-the-art":[86],"techniques":[87],"pattern":[90],"recognition":[91],"to":[95],"implement":[96],"cognitive":[97],"models":[98],"can":[100],"process":[101],"sensor":[103],"data":[104],"without":[105],"need":[107],"for":[108],"human":[109],"transcription":[110],"or":[111],"labeling.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":23},{"year":2012,"cited_by_count":20}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}