{"id":"https://openalex.org/W4400621949","doi":"https://doi.org/10.21437/odyssey.2024-19","title":"Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization","display_name":"Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4400621949","doi":"https://doi.org/10.21437/odyssey.2024-19"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2024-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2024-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2024)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01J1SXAZEX47RPG4YH3XKHGXJW/file/01J1SXCKRFS60CVYW15WKZ63MR.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022199264","display_name":"Jenthe Thienpondt","orcid":"https://orcid.org/0000-0001-5990-722X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Jenthe Thienpondt","raw_affiliation_strings":["Department of Electronics and Information Systems Ghent University -imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems Ghent University -imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046536366","display_name":"Kris Demuynck","orcid":"https://orcid.org/0000-0001-8525-7160"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kris Demuynck","raw_affiliation_strings":["Department of Electronics and Information Systems Ghent University -imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems Ghent University -imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022199264"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9948999881744385,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9948999881744385,"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/T10860","display_name":"Speech and Audio Processing","score":0.9728999733924866,"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":0.9190000295639038,"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":0.9029442071914673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7209680080413818},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6889658570289612},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.642550528049469},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4624974727630615},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4439370632171631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32861843705177307},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2503596842288971}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9029442071914673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209680080413818},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6889658570289612},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.642550528049469},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4624974727630615},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4439370632171631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32861843705177307},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2503596842288971}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/odyssey.2024-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2024-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2024)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01J1SXAZEX47RPG4YH3XKHGXJW","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01J1SXAZEX47RPG4YH3XKHGXJW","pdf_url":"https://biblio.ugent.be/publication/01J1SXAZEX47RPG4YH3XKHGXJW/file/01J1SXCKRFS60CVYW15WKZ63MR.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of The Speaker and Language Recognition Workshop (Odyssey 2024)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01J1SXAZEX47RPG4YH3XKHGXJW","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01J1SXAZEX47RPG4YH3XKHGXJW","pdf_url":"https://biblio.ugent.be/publication/01J1SXAZEX47RPG4YH3XKHGXJW/file/01J1SXCKRFS60CVYW15WKZ63MR.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of The Speaker and Language Recognition Workshop (Odyssey 2024)","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400621949.pdf","grobid_xml":"https://content.openalex.org/works/W4400621949.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1506438021","https://openalex.org/W2148613904","https://openalex.org/W2165874743","https://openalex.org/W2219249508","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2972949456","https://openalex.org/W3024541814","https://openalex.org/W3024869864","https://openalex.org/W3127686677","https://openalex.org/W3134299941","https://openalex.org/W3141035251","https://openalex.org/W3143367551","https://openalex.org/W3157070662","https://openalex.org/W3167533889","https://openalex.org/W3196595845","https://openalex.org/W3205878676","https://openalex.org/W4297841362","https://openalex.org/W4372267289","https://openalex.org/W4372268583","https://openalex.org/W4385822353","https://openalex.org/W4386044452","https://openalex.org/W4391021719"],"related_works":["https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2144470400","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"Current":[0],"speaker":[1,14,33,55,68,97,104,109],"diarization":[2,56,105,130],"systems":[3],"rely":[4],"on":[5,17,123],"an":[6,78,84],"external":[7,79],"voice":[8],"activity":[9],"detection":[10],"model":[11,43],"prior":[12],"to":[13],"embedding":[15,34,69,115],"extraction":[16],"the":[18,28,63,72,88,91,124],"detected":[19],"speech":[20],"segments.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"establish":[26],"that":[27],"attention":[29,93],"system":[30,94],"of":[31,77,87,90],"a":[32,38,102],"extractor":[35],"acts":[36],"as":[37],"weakly":[39],"supervised":[40,51],"internal":[41],"VAD":[42,52,64,80,113],"and":[44,66,74,100,114,127],"performs":[45],"equally":[46],"or":[47],"better":[48],"than":[49],"comparable":[50],"systems.":[53],"Subsequently,":[54],"can":[57],"be":[58],"performed":[59],"efficiently":[60],"by":[61],"extracting":[62],"logits":[65],"corresponding":[67],"simultaneously,":[70],"alleviating":[71],"need":[73],"computational":[75],"overhead":[76],"model.":[81],"We":[82],"provide":[83],"extensive":[85],"analysis":[86],"behavior":[89],"frame-level":[92],"in":[95],"current":[96],"verification":[98],"models":[99],"propose":[101],"novel":[103],"pipeline":[106],"using":[107],"ECAPA2":[108],"embeddings":[110],"for":[111],"both":[112],"extraction.":[116],"The":[117],"proposed":[118],"strategy":[119],"gains":[120],"state-of-the-art":[121],"performance":[122],"AMI,":[125],"VoxConverse":[126],"DIHARD":[128],"III":[129],"benchmarks.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
