{"id":"https://openalex.org/W4415092912","doi":"https://doi.org/10.1007/978-3-032-07959-6_21","title":"Ensembling Synchronisation-Based and\u00a0Face-Voice Association Paradigms for\u00a0Robust Active Speaker Detection in\u00a0Egocentric Recordings","display_name":"Ensembling Synchronisation-Based and\u00a0Face-Voice Association Paradigms for\u00a0Robust Active Speaker Detection in\u00a0Egocentric Recordings","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4415092912","doi":"https://doi.org/10.1007/978-3-032-07959-6_21"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-07959-6_21","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-07959-6_21","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5007683838","display_name":"Jason Clarke","orcid":"https://orcid.org/0000-0003-1897-704X"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jason Clarke","raw_affiliation_strings":["Speech and Hearing (SPandH), School of Computer Science, The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing (SPandH), School of Computer Science, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047046960","display_name":"Yoshihiko Gotoh","orcid":"https://orcid.org/0000-0003-1668-0867"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yoshihiko Gotoh","raw_affiliation_strings":["Speech and Hearing (SPandH), School of Computer Science, The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing (SPandH), School of Computer Science, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027797344","display_name":"Stefan Goetze","orcid":"https://orcid.org/0000-0003-1044-7343"},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Stefan Goetze","raw_affiliation_strings":["South Westphalia University of Applied Sciences, Iserlohn, Germany","Speech and Hearing (SPandH), School of Computer Science, The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"South Westphalia University of Applied Sciences, Iserlohn, Germany","institution_ids":["https://openalex.org/I3130920692"]},{"raw_affiliation_string":"Speech and Hearing (SPandH), School of Computer Science, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007683838"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70550162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"301"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/robustness","display_name":"Robustness (evolution)","score":0.6754000186920166},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6251000165939331},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.5095999836921692},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46650001406669617},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4244000017642975},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4203000068664551},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.37869998812675476},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3686000108718872},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.34700000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8841000199317932},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6754000186920166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6484000086784363},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6251000165939331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985000133514404},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C153668964","wikidata":"https://www.wikidata.org/wiki/Q27636","display_name":"Majority rule","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30169999599456787},{"id":"https://openalex.org/C11560541","wikidata":"https://www.wikidata.org/wiki/Q1756025","display_name":"Replay attack","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-032-07959-6_21","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-07959-6_21","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:eprints.whiterose.ac.uk:230329","is_oa":false,"landing_page_url":"https://orcid.org/0000-0002-1032-6472>,","pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2168996682","https://openalex.org/W2341528187","https://openalex.org/W2808631503","https://openalex.org/W2910922521","https://openalex.org/W2963839617","https://openalex.org/W3006276840","https://openalex.org/W3015671919","https://openalex.org/W3016098309","https://openalex.org/W3024869864","https://openalex.org/W3034702511","https://openalex.org/W3035739915","https://openalex.org/W3101998545","https://openalex.org/W3154848313","https://openalex.org/W3169129566","https://openalex.org/W3172472082","https://openalex.org/W3177326298","https://openalex.org/W3206008172","https://openalex.org/W4214701094","https://openalex.org/W4225302874","https://openalex.org/W4283382486","https://openalex.org/W4312268709","https://openalex.org/W4312466984","https://openalex.org/W4372341093","https://openalex.org/W4385822320","https://openalex.org/W4386075783","https://openalex.org/W4391021777","https://openalex.org/W4402754289","https://openalex.org/W4408352877","https://openalex.org/W4408353541"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
