{"id":"https://openalex.org/W2130575599","doi":"https://doi.org/10.1109/cvprw.2008.4563183","title":"Speaker detection using the timing structure of lip motion and sound","display_name":"Speaker detection using the timing structure of lip motion and sound","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2130575599","doi":"https://doi.org/10.1109/cvprw.2008.4563183","mag":"2130575599"},"language":"en","primary_location":{"id":"doi:10.1109/cvprw.2008.4563183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw.2008.4563183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","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/A5113676844","display_name":"Yu Horii","orcid":null},"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"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yu Horii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111822895","display_name":"Hiroaki Kawashima","orcid":null},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroaki Kawashima","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102940139","display_name":"Takashi Matsuyama","orcid":"https://orcid.org/0000-0003-0666-0512"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Matsuyama","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113676844"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1628013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.996999979019165,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7863409519195557},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7168502807617188},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5989249348640442},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5809564590454102},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5593944191932678},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5272998809814453},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5035962462425232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5011944770812988},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4756873846054077},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.42197465896606445},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41911640763282776},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.411730021238327},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3343169093132019},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.298231840133667},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14408835768699646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863409519195557},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7168502807617188},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5989249348640442},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5809564590454102},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5593944191932678},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5272998809814453},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5035962462425232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011944770812988},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4756873846054077},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.42197465896606445},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41911640763282776},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.411730021238327},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3343169093132019},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.298231840133667},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14408835768699646},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvprw.2008.4563183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw.2008.4563183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.592.4381","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.592.4381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vision.kuee.kyoto-u.ac.jp/~hiroaki/publication/Horii_2008_CVPR4HB.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.644.7469","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.644.7469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mplab.ucsd.edu/wp-content/uploads/CVPR2008/WorkShops/data/papers/234.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W348273386","https://openalex.org/W1546163240","https://openalex.org/W1587625526","https://openalex.org/W1915810655","https://openalex.org/W1988874269","https://openalex.org/W2049633694","https://openalex.org/W2071795835","https://openalex.org/W2083393647","https://openalex.org/W2110935301","https://openalex.org/W2133447020","https://openalex.org/W2141823335","https://openalex.org/W2143400343","https://openalex.org/W2182517799","https://openalex.org/W3141741032","https://openalex.org/W6611851769","https://openalex.org/W6632584858","https://openalex.org/W6681231359"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2099333848"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,42,64],"propose":[4],"a":[5,44],"novel":[6],"approach":[7],"to":[8],"speaker":[9,66,92],"detection":[10,67],"by":[11,51,68],"an":[12],"integration":[13],"of":[14,20,28,36,48,56,73,85,89],"audio-visual":[15],"information":[16],"using":[17,86],"the":[18,53,61,70,74,83],"cue":[19],"timing":[21,71],"structure.":[22],"We":[23],"first":[24],"extract":[25],"feature":[26],"sequences":[27],"lip":[29],"motion":[30],"and":[31,33,77],"sound,":[32],"segment":[34],"each":[35],"them":[37],"into":[38],"temporal":[39,54,87],"intervals.":[40,58],"Then,":[41],"construct":[43],"cross-media":[45],"timing-structure":[46],"model":[47],"human":[49],"speech":[50],"learning":[52],"relations":[55,88],"overlapping":[57],"Based":[59],"on":[60],"learned":[62],"model,":[63],"realize":[65],"evaluating":[69],"structure":[72],"observed":[75],"video":[76],"audio.":[78],"Our":[79],"experimental":[80],"result":[81],"shows":[82],"effectiveness":[84],"intervals":[90],"for":[91],"detection.":[93]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}