{"id":"https://openalex.org/W4296069289","doi":"https://doi.org/10.21437/interspeech.2022-10165","title":"Training speaker embedding extractors using multi-speaker audio with unknown speaker boundaries","display_name":"Training speaker embedding extractors using multi-speaker audio with unknown speaker boundaries","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069289","doi":"https://doi.org/10.21437/interspeech.2022-10165"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10165","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10165","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["Omilia -Conversational Intelligence, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Omilia -Conversational Intelligence, Athens, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055201620","display_name":"Ladislav Mo\u0161ner","orcid":"https://orcid.org/0000-0001-8175-2244"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ladislav Mosner","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064238041","display_name":"Old\u0159ich Plchot","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Oldrich Plchot","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043239262","display_name":"Johan Rohdin","orcid":"https://orcid.org/0000-0003-0978-2064"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Johan Rohdin","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","Omilia -Conversational Intelligence, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Omilia -Conversational Intelligence, Athens, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043410084","display_name":"Anna Silnova","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Anna Silnova","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan \u010cernock\u00fd","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, Speech@FIT, Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3373,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54885402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"605","last_page":"609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.7580181360244751},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7217190861701965},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6934933662414551},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6704350709915161},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6686878204345703},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.42213401198387146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2888423204421997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580181360244751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7217190861701965},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6934933662414551},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6704350709915161},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6686878204345703},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.42213401198387146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2888423204421997}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10165","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10165","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1319050382","display_name":null,"funder_award_id":"19-26934X","funder_id":"https://openalex.org/F4320321006","funder_display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky"},{"id":"https://openalex.org/G1454328438","display_name":"Exchanges for SPEech ReseArch aNd TechnOlogies","funder_award_id":"101007666","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2364254700","display_name":"Real time network, text, and speaker analytics for combating organized crime","funder_award_id":"833635","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2629758493","display_name":null,"funder_award_id":"LM2018140","funder_id":"https://openalex.org/F4320321006","funder_display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"Horizon2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7545815938","display_name":null,"funder_award_id":"LM2018140","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321006","display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","ror":"https://ror.org/01pv73b02"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2010792435","https://openalex.org/W2110119381","https://openalex.org/W2150769028","https://openalex.org/W2159591770","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2302255633","https://openalex.org/W2502312327","https://openalex.org/W2516764878","https://openalex.org/W2604379605","https://openalex.org/W2726515241","https://openalex.org/W2746791238","https://openalex.org/W2808631503","https://openalex.org/W2889233255","https://openalex.org/W2890964092","https://openalex.org/W2914064142","https://openalex.org/W2938358845","https://openalex.org/W2963449399","https://openalex.org/W2972680151","https://openalex.org/W2972705840","https://openalex.org/W3024869864","https://openalex.org/W3025831232","https://openalex.org/W3095212884","https://openalex.org/W3109225549","https://openalex.org/W3163187953","https://openalex.org/W3166898278","https://openalex.org/W3194763370","https://openalex.org/W3196906655","https://openalex.org/W3207595101","https://openalex.org/W4206499725","https://openalex.org/W4220739185","https://openalex.org/W4221167533","https://openalex.org/W4286981691"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2144470400","https://openalex.org/W2140022733","https://openalex.org/W2911612049"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,16,73,83],"demonstrate":[4],"a":[5,49,61,69,78],"method":[6],"for":[7],"training":[8,57,71],"speaker":[9,51],"embedding":[10,81],"extractors":[11],"using":[12,18],"weak":[13],"annotation.More":[14],"specifically,":[15],"are":[17,74],"the":[19,24,27,36,39,43],"full":[20],"VoxCeleb":[21],"recordings":[22],"and":[23,68,90],"name":[25],"of":[26,35,96],"celebrities":[28,40],"appearing":[29],"on":[30],"each":[31],"video":[32],"without":[33],"knowledge":[34],"time":[37],"intervals":[38],"appear":[41],"in":[42,94],"video.We":[44],"show":[45],"that":[46,54],"by":[47],"combining":[48],"baseline":[50],"diarization":[52],"algorithm":[53],"requires":[55],"no":[56],"or":[58],"parameter":[59],"tuning,":[60],"modified":[62],"loss":[63],"with":[64,85],"aggregation":[65,88],"over":[66],"segments,":[67],"two-stage":[70],"approach,":[72],"able":[75],"to":[76],"train":[77],"competitive":[79],"ResNet-based":[80],"extractor.Finally,":[82],"experiment":[84],"two":[86],"different":[87],"functions":[89],"analyze":[91],"their":[92,97],"behaviour":[93],"terms":[95],"gradients.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2025-10-10T00:00:00"}