{"id":"https://openalex.org/W2039842384","doi":"https://doi.org/10.1109/apsipa.2014.7041584","title":"Speaker diarization based on audio-visual integration for smart posterboard","display_name":"Speaker diarization based on audio-visual integration for smart posterboard","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2039842384","doi":"https://doi.org/10.1109/apsipa.2014.7041584","mag":"2039842384"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2014.7041584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2014.7041584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific","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/A5103010851","display_name":"Yukoh Wakabayashi","orcid":"https://orcid.org/0000-0001-8846-3699"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukoh Wakabayashi","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058775745","display_name":"Koji Inoue","orcid":"https://orcid.org/0000-0002-2929-2559"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koji Inoue","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023501753","display_name":"Hiromasa Yoshimoto","orcid":"https://orcid.org/0000-0001-9702-2879"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiromasa Yoshimoto","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4625","issue":null,"first_page":"1","last_page":"4"},"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":0.9998999834060669,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8873543739318848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.811336100101471},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6038805246353149},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4191345274448395},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41265612840652466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36232513189315796},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2282169759273529}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8873543739318848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811336100101471},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6038805246353149},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4191345274448395},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41265612840652466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36232513189315796},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2282169759273529}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2014.7041584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2014.7041584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W76597279","https://openalex.org/W1876378865","https://openalex.org/W2017835752","https://openalex.org/W2025905156","https://openalex.org/W2046317813","https://openalex.org/W2098013184","https://openalex.org/W2113638573","https://openalex.org/W2130992468","https://openalex.org/W2141398670","https://openalex.org/W2153842971","https://openalex.org/W2594833372","https://openalex.org/W6603233860","https://openalex.org/W6639431793","https://openalex.org/W6679443918","https://openalex.org/W6682756210"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"We":[0,12,59],"present":[1],"a":[2],"speaker":[3],"diarization":[4,57],"method":[5,82],"based":[6],"on":[7],"an":[8],"audio-visual":[9],"integration":[10,62,76],"approach.":[11],"deal":[13],"with":[14],"poster":[15,71],"conversations":[16,72],"which":[17,83],"are":[18,26],"more":[19],"challenging":[20],"than":[21],"general":[22],"meetings,":[23],"because":[24],"participants":[25],"moving":[27],"freely":[28],"and":[29,65],"the":[30,75,80],"audience":[31],"utter":[32],"infrequently.":[33],"In":[34],"this":[35],"case,":[36],"it":[37],"is":[38],"difficult":[39],"to":[40,55],"detect":[41],"\"who":[42],"spoke":[43],"when\"":[44],"by":[45],"only":[46],"using":[47],"acoustic":[48,85],"information.":[49],"Therefore":[50],"we":[51],"incorporate":[52],"visual":[53],"information":[54,86],"improve":[56],"accuracy.":[58],"propose":[60],"two":[61],"methods:":[63],"rule-based":[64],"stochastic":[66],"method.":[67],"Experiments":[68],"in":[69],"real":[70],"show":[73],"that":[74],"methods":[77],"significantly":[78],"outperform":[79],"baseline":[81],"uses":[84],"only.":[87]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}