{"id":"https://openalex.org/W2131459862","doi":"https://doi.org/10.1109/icassp.2011.5947476","title":"Using multiple visual tandem streams in audio-visual speech recognition","display_name":"Using multiple visual tandem streams in audio-visual speech recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2131459862","doi":"https://doi.org/10.1109/icassp.2011.5947476","mag":"2131459862"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5085714936","display_name":"\u0130brahim Sayg\u0131n Topkaya","orcid":null},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ibrahim Saygin Topkaya","raw_affiliation_strings":["Vision and Pattern Analysis Laboratory, Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul, Turkey","Vision and Pattern Analysis Laboratory, Sabanci University, Faculty of Engineering and Natural Sciences, Istanbul, Turkey#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vision and Pattern Analysis Laboratory, Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul, Turkey","institution_ids":["https://openalex.org/I134235054"]},{"raw_affiliation_string":"Vision and Pattern Analysis Laboratory, Sabanci University, Faculty of Engineering and Natural Sciences, Istanbul, Turkey#TAB#","institution_ids":["https://openalex.org/I134235054"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Vision and Pattern Analysis Laboratory, Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul, Turkey","Vision and Pattern Analysis Laboratory, Sabanci University, Faculty of Engineering and Natural Sciences, Istanbul, Turkey#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vision and Pattern Analysis Laboratory, Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul, Turkey","institution_ids":["https://openalex.org/I134235054"]},{"raw_affiliation_string":"Vision and Pattern Analysis Laboratory, Sabanci University, Faculty of Engineering and Natural Sciences, Istanbul, Turkey#TAB#","institution_ids":["https://openalex.org/I134235054"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I134235054"],"apc_list":null,"apc_paid":null,"fwci":0.278,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49139499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2002","issue":null,"first_page":"4988","last_page":"4991"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11447","display_name":"Blind Source Separation Techniques","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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8261507749557495},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7772080898284912},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6779857873916626},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5960653424263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5926939845085144},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5673388242721558},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5483669638633728},{"id":"https://openalex.org/keywords/tandem","display_name":"Tandem","score":0.4576948285102844},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4457293152809143},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.44494277238845825},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.328033983707428},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22411179542541504}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8261507749557495},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7772080898284912},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6779857873916626},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5960653424263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5926939845085144},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5673388242721558},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5483669638633728},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.4576948285102844},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4457293152809143},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.44494277238845825},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.328033983707428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22411179542541504},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2011.5947476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:research.sabanciuniv.edu:18469","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402254","display_name":"Sabanci University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134235054","host_organization_name":"Sabanc\u0131 \u00dcniversitesi","host_organization_lineage":["https://openalex.org/I134235054"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.968.5780","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.968.5780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.sabanciuniv.edu/18469/1/saygin_icassp1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.980.3504","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.980.3504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mirlab.org/conference_papers/International_Conference/ICASSP%202011/pdfs/0004988.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W1633840029","https://openalex.org/W1947735963","https://openalex.org/W1978380426","https://openalex.org/W2002342963","https://openalex.org/W2073039128","https://openalex.org/W2095307689","https://openalex.org/W2096391593","https://openalex.org/W2102512156","https://openalex.org/W2105594594","https://openalex.org/W2116418373","https://openalex.org/W2121486117","https://openalex.org/W2150387026","https://openalex.org/W2165712214","https://openalex.org/W2980286501","https://openalex.org/W3021489810","https://openalex.org/W3140954725","https://openalex.org/W6674975915","https://openalex.org/W6677158943","https://openalex.org/W6768798221"],"related_works":["https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2082284720","https://openalex.org/W2084326697","https://openalex.org/W2194396582","https://openalex.org/W2027903142","https://openalex.org/W2116722627","https://openalex.org/W2537260108","https://openalex.org/W2354322608","https://openalex.org/W2379938888"],"abstract_inverted_index":{"The":[0],"method":[1],"which":[2,46],"is":[3,82],"called":[4],"the":[5,31,58,79,94,126],"\"tandem":[6],"approach\"":[7],"in":[8,24,38,78,84,97,103],"speech":[9,40],"recognition":[10,41,95],"has":[11],"been":[12],"shown":[13,83],"to":[14,50,105,125],"increase":[15],"performance":[16,122],"by":[17],"using":[18,34,42,88],"classifier":[19],"posterior":[20],"probabilities":[21],"as":[22,75,123],"observations":[23],"a":[25,43],"hidden":[26,62,116],"Markov":[27,63,117],"model.":[28,80,128],"We":[29,56],"study":[30],"effect":[32],"of":[33,60],"visual":[35,53,66,90,111],"tandem":[36,54,67,91],"features":[37,68,92],"audio-visual":[39],"novel":[44],"setup":[45],"uses":[47],"multiple":[48,52,89],"classifiers":[49,72],"obtain":[51,120],"features.":[55],"adopt":[57],"approach":[59],"multi-stream":[61],"models":[64,118],"where":[65],"from":[69],"two":[70],"different":[71],"are":[73],"considered":[74],"additional":[76],"streams":[77],"It":[81],"our":[85],"experiments":[86],"that":[87],"improve":[93],"accuracy":[96],"various":[98],"noise":[99],"conditions.":[100],"In":[101],"addition,":[102],"order":[104],"handle":[106],"asynchrony":[107],"between":[108],"audio":[109],"and":[110,119],"observations,":[112],"we":[113],"employ":[114],"coupled":[115],"improved":[121],"compared":[124],"synchronous":[127]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}