{"id":"https://openalex.org/W2001752885","doi":"https://doi.org/10.1145/1647314.1647331","title":"Cache-based language model adaptation using visual attention for ASR in meeting scenarios","display_name":"Cache-based language model adaptation using visual attention for ASR in meeting scenarios","publication_year":2009,"publication_date":"2009-11-02","ids":{"openalex":"https://openalex.org/W2001752885","doi":"https://doi.org/10.1145/1647314.1647331","mag":"2001752885"},"language":"en","primary_location":{"id":"doi:10.1145/1647314.1647331","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1647314.1647331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 international conference on Multimodal interfaces","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/A5043617655","display_name":"Neil Cooke","orcid":"https://orcid.org/0000-0003-2247-0663"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Neil J. Cooke","raw_affiliation_strings":["University of Birmingham, Birmingham, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Birmingham, Birmingham, United Kingdom","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079477816","display_name":"Martin Russell","orcid":"https://orcid.org/0000-0002-8324-4961"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin J. Russell","raw_affiliation_strings":["University of Birmingham, Birmingham, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Birmingham, Birmingham, United Kingdom","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043617655"],"corresponding_institution_ids":["https://openalex.org/I79619799"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.08437119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9905999898910522,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9757000207901001,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/perplexity","display_name":"Perplexity","score":0.9426361322402954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8693193197250366},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7767074108123779},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6990846991539001},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.646636962890625},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6083157062530518},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4788239300251007},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.47814667224884033},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39232751727104187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3740227520465851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33792605996131897},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09510064125061035},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08141449093818665}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9426361322402954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8693193197250366},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7767074108123779},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6990846991539001},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.646636962890625},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6083157062530518},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4788239300251007},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.47814667224884033},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39232751727104187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3740227520465851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33792605996131897},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09510064125061035},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08141449093818665},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1647314.1647331","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1647314.1647331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 international conference on Multimodal interfaces","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.618.5500","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.618.5500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eee.bham.ac.uk/cooken/CachebasedLMUsingVA_MLMI09_NeilCooke.pdf","raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/b0cecec4-5465-45ca-85c2-a0c9485e5f08","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/b0cecec4-5465-45ca-85c2-a0c9485e5f08","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cooke, N & Russell, M 2009, 'Cache-based language model adaptation using visual attention for ASR in meeting scenarios', Paper presented at Proceedings of the 2009 international conference on Multimodal interfaces - ICMI-MLMI '09, New York, New York, USA, 4/11/09 pp. 87-90. https://doi.org/10.1145/1647314.1647331","raw_type":"conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W152523715","https://openalex.org/W171075636","https://openalex.org/W758629932","https://openalex.org/W1517003397","https://openalex.org/W1569447338","https://openalex.org/W1631260214","https://openalex.org/W2097927681","https://openalex.org/W2106892467","https://openalex.org/W2118142207","https://openalex.org/W2119609990","https://openalex.org/W2127836646","https://openalex.org/W2950186769","https://openalex.org/W4242131330","https://openalex.org/W4254373586"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2787311093"],"abstract_inverted_index":{"In":[0,28],"a":[1,38,67],"typical":[2],"group":[3],"meeting":[4,115],"involving":[5],"discussion":[6],"and":[7,22],"col-laboration,":[8],"people":[9],"look":[10],"at":[11,14,24,42],"one":[12],"another,":[13],"shared":[15],"informa-tion":[16],"resources":[17],"such":[18],"as":[19],"presentation":[20],"material,":[21],"also":[23],"nothing":[25],"in":[26,109,114],"particular.":[27],"this":[29],"work":[30,98],"we":[31],"investigate":[32],"whether":[33],"the":[34,45,63,78,88,100],"knowledge":[35],"of":[36,47,80],"what":[37],"person":[39],"is":[40,60],"looking":[41],"may":[43],"improve":[44],"performance":[46],"Automatic":[48],"Speech":[49],"Recognition":[50],"(ASR).":[51],"A":[52],"framework":[53,74],"for":[54,102],"cache":[55,64],"Language":[56],"Model":[57],"(LM)":[58],"adaptation":[59,81,105],"proposed":[61],"with":[62],"based":[65],"on":[66,87],"person\u2019s":[68],"Visual":[69],"At-tention":[70],"(VA)":[71],"sequence.":[72],"The":[73],"attempts":[75],"to":[76],"measure":[77],"appropriateness":[79],"from":[82],"VA":[83,107],"sequence":[84],"charac-teristics.":[85],"Evaluation":[86],"AMI":[89],"Meeting":[90],"corpus":[91],"data":[92],"shows":[93],"reduced":[94],"LM":[95,104],"perplexity.":[96],"This":[97],"demonstrates":[99],"poten-tial":[101],"cache-based":[103],"using":[106],"information":[108],"large":[110],"vocabulary":[111],"ASR":[112],"deployed":[113],"scenarios.":[116]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
