{"id":"https://openalex.org/W2103205919","doi":"https://doi.org/10.1109/icassp.2004.1326011","title":"Robust multimodal understanding","display_name":"Robust multimodal understanding","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2103205919","doi":"https://doi.org/10.1109/icassp.2004.1326011","mag":"2103205919"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-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/A5111475783","display_name":"Srinivas Bangalore","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S. Bangalore","raw_affiliation_strings":["AT and T Research Laboratories, Florham Park, NJ, USA","AT&T Lab. Res., USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Lab. Res., USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058476987","display_name":"Michael Johnston","orcid":"https://orcid.org/0000-0001-9869-6357"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Johnston","raw_affiliation_strings":["AT and T Research Laboratories, Florham Park, NJ, USA","AT&T Lab. Res., USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Lab. Res., USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111475783"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":1.3491,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84944825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":1.0,"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":1.0,"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":0.9966999888420105,"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/T10028","display_name":"Topic Modeling","score":0.9926000237464905,"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":0.8099605441093445},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7919551134109497},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.5935919880867004},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4993419647216797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49498623609542847},{"id":"https://openalex.org/keywords/multimodal-therapy","display_name":"Multimodal therapy","score":0.45268312096595764},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.44587236642837524},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.430225670337677},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41743800044059753},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.06688499450683594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8099605441093445},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7919551134109497},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.5935919880867004},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4993419647216797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49498623609542847},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.45268312096595764},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.44587236642837524},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.430225670337677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41743800044059753},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.06688499450683594},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C141071460","wikidata":"https://www.wikidata.org/wiki/Q40821","display_name":"Surgery","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4000000059604645,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W200755699","https://openalex.org/W1518357715","https://openalex.org/W1535449205","https://openalex.org/W1538417395","https://openalex.org/W1538585905","https://openalex.org/W1540371141","https://openalex.org/W1574174742","https://openalex.org/W1623072288","https://openalex.org/W1980365852","https://openalex.org/W2009563696","https://openalex.org/W2033010331","https://openalex.org/W2044755726","https://openalex.org/W2083325968","https://openalex.org/W2097387597","https://openalex.org/W2103290541","https://openalex.org/W2108108911","https://openalex.org/W2126891226","https://openalex.org/W2140454176","https://openalex.org/W2153501885","https://openalex.org/W2162455891","https://openalex.org/W2169315475","https://openalex.org/W2951562155","https://openalex.org/W2952238071","https://openalex.org/W3088781800","https://openalex.org/W6631961239","https://openalex.org/W6632223008","https://openalex.org/W6636392717","https://openalex.org/W6674768517","https://openalex.org/W6676197023","https://openalex.org/W7042882705"],"related_works":["https://openalex.org/W4380355808","https://openalex.org/W2035104213","https://openalex.org/W2558617677","https://openalex.org/W2013013717","https://openalex.org/W2342456189","https://openalex.org/W66256988","https://openalex.org/W2068964259","https://openalex.org/W2240967841","https://openalex.org/W1987340722","https://openalex.org/W2791686160"],"abstract_inverted_index":{"Contemporary":[0],"multimodal":[1,41,48,70,87],"prototypes":[2],"provide":[3],"an":[4],"excellent":[5],"proof":[6],"of":[7,17,40,85],"concept":[8],"but":[9],"are":[10],"not":[11],"sufficiently":[12],"robust":[13,69],"in":[14,27,82],"their":[15],"handling":[16],"user":[18],"input":[19],"to":[20,33,43,68],"be":[21,51],"adopted":[22],"by":[23,76],"real":[24],"users":[25],"engaged":[26],"complex":[28],"tasks.":[29],"Our":[30],"goal":[31],"is":[32],"investigate":[34],"techniques":[35],"that":[36],"improve":[37],"the":[38,44,83],"robustness":[39],"understanding":[42],"point":[45],"where":[46],"effective":[47],"interfaces":[49],"can":[50],"made":[52],"feasible.":[53],"We":[54,72],"present":[55],"two":[56],"different":[57],"approaches":[58,75],"-":[59],"a":[60,65,86],"pattern-matching":[61],"based":[62],"approach":[63,67],"and":[64],"classification-based":[66],"understanding.":[71],"compare":[73],"these":[74],"evaluating":[77],"them":[78],"on":[79],"data":[80],"collected":[81],"context":[84],"conversational":[88],"system.":[89]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
