{"id":"https://openalex.org/W1574972348","doi":"https://doi.org/10.21437/eurospeech.2003-635","title":"A visual context-aware multimodal system for spoken language processing","display_name":"A visual context-aware multimodal system for spoken language processing","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W1574972348","doi":"https://doi.org/10.21437/eurospeech.2003-635","mag":"1574972348"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-635","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5103287143","display_name":"Niloy Mukherjee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niloy Mukherjee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","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":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2554,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.46085489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2273","last_page":"2276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.996999979019165,"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":0.996999979019165,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9883000254631042,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9812999963760376,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8061119914054871},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5750817060470581},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5513321757316589},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49585089087486267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4354023337364197},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.42959317564964294},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.42019689083099365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.419153094291687},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3075162172317505},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2571302652359009},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.08333250880241394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061119914054871},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5750817060470581},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5513321757316589},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49585089087486267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4354023337364197},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.42959317564964294},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.42019689083099365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.419153094291687},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3075162172317505},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2571302652359009},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.08333250880241394},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2003-635","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.9729","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.9729","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/niloy-euro03.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"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":10,"referenced_works":["https://openalex.org/W47415966","https://openalex.org/W1598442403","https://openalex.org/W1606365662","https://openalex.org/W2020755048","https://openalex.org/W2027123861","https://openalex.org/W2100506586","https://openalex.org/W2107697882","https://openalex.org/W2121227244","https://openalex.org/W2156050092","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2035104213","https://openalex.org/W2240967841","https://openalex.org/W2791686160","https://openalex.org/W1587348481","https://openalex.org/W1513257435","https://openalex.org/W2289840258","https://openalex.org/W2503352526","https://openalex.org/W2968405290","https://openalex.org/W2960696728","https://openalex.org/W2114040463"],"abstract_inverted_index":{"Recent":[0],"psycholinguistic":[1],"experiments":[2],"show":[3],"that":[4,45],"acoustic":[5],"and":[6,32,70,109],"syntactic":[7],"aspects":[8],"of":[9,23,49,84,88,90,114],"online":[10],"speech":[11,30,119],"processing":[12,31],"are":[13],"influenced":[14],"by":[15,42],"visual":[16,25,50,115],"context":[17,26],"through":[18],"cross-modal":[19],"influences.":[20],"During":[21],"interpretation":[22],"speech,":[24],"seems":[27],"to":[28,53,117],"steer":[29,118],"vice":[33],"versa.":[34],"We":[35],"present":[36],"a":[37,68,71,76,98,104,111],"real-time":[38],"multimodal":[39],"system":[40,65,102],"motivated":[41],"these":[43],"findings":[44],"performs":[46],"early":[47],"integration":[48],"contextual":[51],"information":[52],"recognize":[54],"the":[55,80,101],"most":[56],"likely":[57,125],"word":[58,126],"sequences":[59],"in":[60],"spoken":[61],"language":[62,107],"utterances.":[63],"The":[64],"first":[66],"acquires":[67],"grammar":[69],"visually":[72],"grounded":[73],"lexicon":[74],"from":[75],"&amp;quot;show-and-tell&amp;quot;":[77],"procedure":[78],"where":[79],"training":[81],"input":[82],"consists":[83],"camera":[85],"images":[86],"consisting":[87],"sets":[89],"objects":[91],"paired":[92],"with":[93],"verbal":[94],"object":[95],"descriptions.":[96],"Given":[97],"new":[99],"scene,":[100],"generates":[103],"dynamic":[105,112],"visually-grounded":[106],"model":[108,113],"drives":[110],"attention":[116],"recognition":[120],"search":[121],"paths":[122],"towards":[123],"more":[124],"sequences.":[127]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
