{"id":"https://openalex.org/W1968813115","doi":"https://doi.org/10.1109/icassp.2002.5745029","title":"Multi-stream product modal audio-visual integration strategy for robust adaptive speech recognition","display_name":"Multi-stream product modal audio-visual integration strategy for robust adaptive speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W1968813115","doi":"https://doi.org/10.1109/icassp.2002.5745029","mag":"1968813115"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745029","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/A5109042393","display_name":"Sabri Gurbuz","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sabri Gurbuz","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087689483","display_name":"Zekeriya T\u00dcFEKC\u0130","orcid":"https://orcid.org/0000-0001-7835-2741"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zekeriya Tufekci","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101982814","display_name":"Eric Patterson","orcid":"https://orcid.org/0009-0005-6953-032X"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Patterson","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034808001","display_name":"J.N. Gowdy","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John N. Gowdy","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109042393"],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":null,"apc_paid":null,"fwci":1.6488,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8075278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"2021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598285675048828},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6969693899154663},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6350728273391724},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.48759618401527405},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.460823655128479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3378276824951172},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.11834728717803955},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07484018802642822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598285675048828},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6969693899154663},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6350728273391724},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.48759618401527405},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.460823655128479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3378276824951172},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11834728717803955},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07484018802642822},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5745029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745029","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.467.4931","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.467.4931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clemson.edu/ces/speech/papers/sabri_icassp2002.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W57938005","https://openalex.org/W1520736967","https://openalex.org/W1523010034","https://openalex.org/W1554901277","https://openalex.org/W1572240262","https://openalex.org/W1576996184","https://openalex.org/W1869491686","https://openalex.org/W1929897159","https://openalex.org/W1959749536","https://openalex.org/W2118977726","https://openalex.org/W6602324134","https://openalex.org/W6631338322","https://openalex.org/W6633115111"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2893763841","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W2778699561","https://openalex.org/W2785586734","https://openalex.org/W2995996972","https://openalex.org/W2312116756","https://openalex.org/W4304891817","https://openalex.org/W4306916306"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"extend":[4],"an":[5,76],"existing":[6],"audio-only":[7,115],"automatic":[8,16],"speech":[9,17,30],"recognizer":[10,116,123],"to":[11,124],"implement":[12],"a":[13,24,61],"multi-stream":[14,25,42,52],"audio-visual":[15,29,43,122],"recognition":[18,79],"(AV-ASR)":[19],"system.":[20],"Our":[21],"method":[22],"forms":[23],"feature":[26],"vector":[27],"from":[28,86,111],"data,":[31],"computes":[32],"the":[33,39,51,87,99,114,120,128],"statistical":[34],"modal":[35,54],"parameters":[36],"probabilities":[37],"on":[38,50],"basis":[40],"of":[41],"features,":[44],"and":[45,64,108,117],"performs":[46],"dynamic":[47],"programming":[48],"jointly":[49],"product":[53],"Hidden":[55],"Markov":[56],"Models":[57],"(MS-PM-HMMs)":[58],"by":[59],"utilizing":[60],"noise":[62,84,109],"type":[63],"signal-to-noise":[65],"ratio":[66],"(SNR)":[67],"based":[68],"stream-weighting":[69],"value.":[70],"Experimental":[71],"results":[72],"are":[73],"presented":[74],"for":[75,81,91],"isolated":[77],"word":[78,100],"task":[80],"eight":[82],"different":[83],"types":[85],"NOISEX":[88],"data":[89],"base":[90],"several":[92,106],"SNR":[93,107],"values.":[94],"The":[95],"proposed":[96],"system":[97],"reduces":[98],"error":[101],"rate":[102],"(WER),":[103],"averaged":[104],"over":[105],"types,":[110],"55.9%":[112],"With":[113],"7.9%":[118],"with":[119],"late-integration":[121],"2.6%":[125],"WER":[126],"in":[127],"validation":[129],"set.":[130]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}