{"id":"https://openalex.org/W1771384906","doi":"https://doi.org/10.21437/interspeech.2009-338","title":"Fusing audio and video information for online speaker diarization","display_name":"Fusing audio and video information for online speaker diarization","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W1771384906","doi":"https://doi.org/10.21437/interspeech.2009-338","mag":"1771384906"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-338","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5036255349","display_name":"Joerg Schmalenstroeer","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Joerg Schmalenstroeer","raw_affiliation_strings":["Paderborn University:"],"affiliations":[{"raw_affiliation_string":"Paderborn University:","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057120698","display_name":"Martin Kelling","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Kelling","raw_affiliation_strings":["Paderborn University:"],"affiliations":[{"raw_affiliation_string":"Paderborn University:","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034723709","display_name":"Volker Leutnant","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Leutnant","raw_affiliation_strings":["Paderborn University, Paderborn, Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University:"],"affiliations":[{"raw_affiliation_string":"Paderborn University:","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036255349"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":1.4284,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79840849,"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":"1163","last_page":"1166"},"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":0.9997000098228455,"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":0.9965000152587891,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8552426099777222},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8472901582717896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6518112421035767},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6332862377166748},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6146632432937622},{"id":"https://openalex.org/keywords/zoom","display_name":"Zoom","score":0.44456925988197327},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.41907554864883423},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3846328854560852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3547471761703491},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.30022501945495605}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8552426099777222},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8472901582717896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6518112421035767},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6332862377166748},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6146632432937622},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.44456925988197327},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.41907554864883423},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3846328854560852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3547471761703491},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.30022501945495605},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-338","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.394.8886","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.394.8886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nt.uni-paderborn.de/public/pubs/2009/ScKeLeHa09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W56805716","https://openalex.org/W146049050","https://openalex.org/W1489183891","https://openalex.org/W1517088255","https://openalex.org/W2052269122","https://openalex.org/W2121647436","https://openalex.org/W2137319143","https://openalex.org/W2163423121","https://openalex.org/W2164598857"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"In":[0,69],"this":[1],"paper":[2],"we":[3,76],"present":[4],"a":[5,17,78,93,108],"system":[6],"for":[7],"identifying":[8],"and":[9,16,41,56,88,96],"localizing":[10],"speakers":[11],"using":[12],"distant":[13],"microphone":[14],"arrays":[15],"steerable":[18],"pantilt-zoom":[19],"camera.":[20],"The":[21],"scenario":[22],"at":[23],"hand":[24],"assumes":[25],"audio":[26,100],"streams":[27],"to":[28,33,52,64,71],"be":[29],"processed":[30],"in":[31],"real-time":[32],"get":[34],"the":[35,54,61,66,99,112],"diarization":[36,67,113],"information":[37,106],"\u201cwho":[38],"spokes":[39],"when":[40],"where":[42],"\u201d":[43],"with":[44],"only":[45],"short":[46],"delays.":[47],"Our":[48],"new":[49],"idea":[50],"is":[51],"fuse":[53],"acoustical":[55],"visual":[57],"observations":[58],"directly":[59],"within":[60],"Viterbi":[62,73],"decoder":[63,74],"improve":[65],"process.":[68],"contrast":[70],"standard":[72],"implementations,":[75],"use":[77],"time":[79],"variant":[80],"transition":[81],"matrix":[82],"generated":[83],"from":[84],"speaker":[85,117],"change":[86],"hypotheses":[87],"location":[89],"information.":[90],"This":[91],"allows":[92],"simultaneous":[94],"segmentation":[95],"classification":[97],"of":[98,111],"stream.":[101],"Experiments":[102],"show,":[103],"that":[104],"video":[105],"enables":[107],"substantial":[109],"improvement":[110],"results.":[114],"Index":[115],"Terms:":[116],"diarization,":[118],"face":[119],"identification,":[120],"acoustic":[121],"scene":[122],"analysis":[123]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
