{"id":"https://openalex.org/W1497970776","doi":"https://doi.org/10.21437/icslp.1998-275","title":"Learning words from natural audio-visual input","display_name":"Learning words from natural audio-visual input","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W1497970776","doi":"https://doi.org/10.21437/icslp.1998-275","mag":"1497970776"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-275","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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/A5004281470","display_name":"Deb Roy","orcid":"https://orcid.org/0000-0002-2780-4768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deb Roy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007176508","display_name":"Alex Pentland","orcid":"https://orcid.org/0000-0002-8053-9983"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Pentland","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":23.9873,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.98677249,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"paper 0551","last_page":"0"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.6801999807357788,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.6801999807357788,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.590499997138977,"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":0.7562848329544067},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6642387509346008},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.6459709405899048},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4420505166053772},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4244537055492401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4242405295372009},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3881993889808655},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3333881199359894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562848329544067},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6642387509346008},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.6459709405899048},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4420505166053772},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4244537055492401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4242405295372009},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3881993889808655},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3333881199359894},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/icslp.1998-275","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.43.3797","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.43.3797","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/icslp98.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.51.4872","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.51.4872","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/Postscript/icslp98.ps.Z","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,43,47],"model":[3,17,41,51],"of":[4,52],"early":[5],"word":[6],"learning":[7],"which":[8],"learns":[9],"from":[10,29],"natural":[11],"audio":[12],"and":[13,25,31,67],"visual":[14],"input.":[15,33],"The":[16],"has":[18],"been":[19],"successfully":[20],"implemented":[21],"to":[22],"learn":[23],"words":[24],"their":[26],"audio-visual":[27],"grounding":[28],"camera":[30],"microphone":[32],"Although":[34],"simple":[35],"in":[36],"its":[37],"current":[38],"form,":[39],"this":[40],"is":[42],"first":[44],"step":[45],"towards":[46],"more":[48],"complete,":[49],"fully-grounded":[50],"language":[53],"acquisition.":[54],"Practical":[55],"applications":[56],"include":[57],"adaptive":[58],"human-machine":[59],"interfaces":[60],"for":[61],"information":[62],"browsing,":[63],"assistive":[64],"technologies,":[65],"education,":[66],"entertainment.":[68]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}