{"id":"https://openalex.org/W2547701628","doi":"https://doi.org/10.1145/2993148.2993172","title":"Active speaker detection with audio-visual co-training","display_name":"Active speaker detection with audio-visual co-training","publication_year":2016,"publication_date":"2016-10-31","ids":{"openalex":"https://openalex.org/W2547701628","doi":"https://doi.org/10.1145/2993148.2993172","mag":"2547701628"},"language":"en","primary_location":{"id":"doi:10.1145/2993148.2993172","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2993148.2993172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/handle/123456789/559697","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045185635","display_name":"Punarjay Chakravarty","orcid":null},"institutions":[{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]},{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Punarjay Chakravarty","raw_affiliation_strings":["KU Leuven, Belgium / iMinds, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven, Belgium / iMinds, Belgium","institution_ids":["https://openalex.org/I39327780","https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045500434","display_name":"Jeroen Zegers","orcid":"https://orcid.org/0000-0002-7098-7168"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jeroen Zegers","raw_affiliation_strings":["KU Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074816094","display_name":"Tinne Tuytelaars","orcid":"https://orcid.org/0000-0003-3307-9723"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tinne Tuytelaars","raw_affiliation_strings":["KU Leuven, Belgium / iMinds, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven, Belgium / iMinds, Belgium","institution_ids":["https://openalex.org/I39327780","https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hugo Van hamme","raw_affiliation_strings":["KU Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045185635"],"corresponding_institution_ids":["https://openalex.org/I39327780","https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":1.0087,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.77771823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"312","last_page":"316"},"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":0.9994999766349792,"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":0.9987000226974487,"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":0.7903649806976318},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7322561740875244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6979847550392151},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5485766530036926},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48108646273612976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46053364872932434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32877838611602783},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.26828980445861816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7903649806976318},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7322561740875244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6979847550392151},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5485766530036926},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48108646273612976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46053364872932434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32877838611602783},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26828980445861816}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2993148.2993172","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2993148.2993172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/559697","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/559697","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM international conference on multimodal interaction - ICMI 2016, Tokyo, Japan, 12-16 November 2016","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/559697","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/559697","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM international conference on multimodal interaction - ICMI 2016, Tokyo, Japan, 12-16 November 2016","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322308","display_name":"KU Leuven","ror":"https://ror.org/05f950310"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W147600081","https://openalex.org/W1546507953","https://openalex.org/W1902027874","https://openalex.org/W2048679005","https://openalex.org/W2065274193","https://openalex.org/W2066348332","https://openalex.org/W2105101328","https://openalex.org/W2135029798","https://openalex.org/W2138761194","https://openalex.org/W2150769028","https://openalex.org/W2154636774","https://openalex.org/W2250436945","https://openalex.org/W2280175689","https://openalex.org/W2287407690","https://openalex.org/W2330149154","https://openalex.org/W2397741330","https://openalex.org/W2403757143","https://openalex.org/W2406415535","https://openalex.org/W2941689885","https://openalex.org/W2953092061","https://openalex.org/W2964152738","https://openalex.org/W2990138404"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"show":[4],"how":[5],"to":[6,25,45,60,87],"co-train":[7],"a":[8,27,34,47,92],"classifier":[9,32,40,86],"for":[10,50],"active":[11,30,62],"speaker":[12,31],"detection":[13],"using":[14,82],"audio-visual":[15],"data.":[16],"First,":[17],"audio":[18,70,94],"Voice":[19],"Activity":[20],"Detection":[21],"(VAD)":[22],"is":[23,41,65,79],"used":[24,44,59],"train":[26,46],"personalized":[28,93],"video-based":[29],"in":[33,42],"weakly":[35,71],"supervised":[36],"fashion.":[37],"The":[38,53],"video":[39,73,85],"turn":[43],"voice":[48,55,95],"model":[49],"each":[51],"person.":[52],"individual":[54],"models":[56],"are":[57],"then":[58],"detect":[61],"speakers.":[63],"There":[64],"no":[66],"manual":[67],"supervision":[68],"-":[69],"supervises":[72],"classification,":[74],"and":[75],"the":[76,83,89],"co-training":[77],"loop":[78],"completed":[80],"by":[81],"trained":[84],"supervise":[88],"training":[90],"of":[91],"classifier.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
