{"id":"https://openalex.org/W3015443711","doi":"https://doi.org/10.1109/icassp40776.2020.9053323","title":"Channel Adversarial Training for Speaker Verification and Diarization","display_name":"Channel Adversarial Training for Speaker Verification and Diarization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015443711","doi":"https://doi.org/10.1109/icassp40776.2020.9053323","mag":"3015443711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.11643","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020396429","display_name":"Chau Luu","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Chau Luu","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020396429"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.9199,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88682053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7094","last_page":"7098"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9961000084877014,"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":0.9898999929428101,"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/discriminative-model","display_name":"Discriminative model","score":0.8314322233200073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.789029598236084},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7627700567245483},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7432326078414917},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.692634642124176},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6267061829566956},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6179258823394775},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5948640704154968},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5880234837532043},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5364127159118652},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.5348039865493774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.518580436706543},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49840855598449707},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.44062909483909607},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41901424527168274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33527690172195435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07499909400939941},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07129856944084167}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8314322233200073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789029598236084},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7627700567245483},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7432326078414917},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.692634642124176},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6267061829566956},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6179258823394775},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5948640704154968},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5880234837532043},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5364127159118652},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.5348039865493774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.518580436706543},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49840855598449707},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.44062909483909607},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41901424527168274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33527690172195435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07499909400939941},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07129856944084167},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.11643","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11643","pdf_url":"https://arxiv.org/pdf/1910.11643","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/cac3db85-4f30-42e0-b3a3-e67117304602","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/cac3db85-4f30-42e0-b3a3-e67117304602","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Luu, C, Bell, P & Renals, S 2020, Channel Adversarial Training for Speaker Verification and Diarization. in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 7094-7098, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9053323","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/cac3db85-4f30-42e0-b3a3-e67117304602","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/cac3db85-4f30-42e0-b3a3-e67117304602","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.11643","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11643","pdf_url":"https://arxiv.org/pdf/1910.11643","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W1965819578","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2395750323","https://openalex.org/W2510867321","https://openalex.org/W2726515241","https://openalex.org/W2770645414","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2883638418","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2916104401","https://openalex.org/W2937328535","https://openalex.org/W2962788262","https://openalex.org/W2963745998","https://openalex.org/W2963777311","https://openalex.org/W2972680151","https://openalex.org/W2972909277","https://openalex.org/W2973099347","https://openalex.org/W2998115938","https://openalex.org/W3103152812","https://openalex.org/W3104862300","https://openalex.org/W6637618735","https://openalex.org/W6746789195"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4312095835","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2144470400"],"abstract_inverted_index":{"Previous":[0],"work":[1],"has":[2],"encouraged":[3],"domain-invariance":[4],"in":[5,68,105,115,124],"deep":[6],"speaker":[7,83],"embedding":[8],"by":[9],"adversarially":[10],"classifying":[11],"the":[12,19,37,40,65],"dataset":[13],"or":[14,42,50],"labelled":[15],"environment":[16],"to":[17,30,56,64,107],"which":[18,28],"generated":[20],"features":[21,32,73],"belong.":[22],"We":[23],"propose":[24],"a":[25,44,69,102,109,120,127,132],"training":[26,53,137],"strategy":[27],"aims":[29],"produce":[31],"that":[33,80],"are":[34,74],"invariant":[35],"at":[36],"granularity":[38],"of":[39,60],"recording":[41,67],"channel,":[43],"finer":[45],"grained":[46],"objective":[47],"than":[48],"dataset-":[49],"environment-invariance.":[51],"By":[52],"an":[54],"adversary":[55],"predict":[57],"whether":[58],"pairs":[59],"same-speaker":[61],"embeddings":[62],"belong":[63],"same":[66],"Siamese":[70],"fashion,":[71],"learned":[72],"discouraged":[75],"from":[76],"utilizing":[77],"channel":[78],"information":[79],"may":[81],"be":[82],"discriminative":[84],"during":[85],"training.":[86],"Experiments":[87],"for":[88],"verification":[89,95],"on":[90,96],"VoxCeleb":[91,113],"and":[92,94,135],"diarization":[93],"CALLHOME":[97],"show":[98],"promising":[99],"improvements":[100],"over":[101,126],"strong":[103],"baseline":[104],"addition":[106],"outperforming":[108],"dataset-adversarial":[110],"model.":[111],"The":[112],"model":[114],"particular":[116],"performs":[117],"well,":[118],"achieving":[119],"4%":[121],"relative":[122],"improvement":[123],"EER":[125],"Kaldi":[128],"baseline,":[129],"while":[130],"using":[131],"similar":[133],"architecture":[134],"less":[136],"data.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}