{"id":"https://openalex.org/W4372269848","doi":"https://doi.org/10.1109/icassp49357.2023.10095305","title":"Margin-Mixup: A Method for Robust Speaker Verification In Multi-Speaker Audio","display_name":"Margin-Mixup: A Method for Robust Speaker Verification In Multi-Speaker Audio","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372269848","doi":"https://doi.org/10.1109/icassp49357.2023.10095305"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01H1430JZHY3CPWF8JXZ0VE06X/file/01H1432PTXT2T8VV5YMT5VC4W8.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":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"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":"Nilesh Madhu","raw_affiliation_strings":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, 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":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022199264"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":1.1764,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80621443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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":0.8283975124359131},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7345399856567383},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6567238569259644},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6392140984535217},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5265931487083435},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.047941744327545166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283975124359131},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7345399856567383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6567238569259644},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6392140984535217},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5265931487083435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.047941744327545166}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01H1430JZHY3CPWF8JXZ0VE06X","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01H1430JZHY3CPWF8JXZ0VE06X","pdf_url":"https://biblio.ugent.be/publication/01H1430JZHY3CPWF8JXZ0VE06X/file/01H1432PTXT2T8VV5YMT5VC4W8.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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781728163277","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01H1430JZHY3CPWF8JXZ0VE06X","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01H1430JZHY3CPWF8JXZ0VE06X","pdf_url":"https://biblio.ugent.be/publication/01H1430JZHY3CPWF8JXZ0VE06X/file/01H1432PTXT2T8VV5YMT5VC4W8.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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781728163277","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372269848.pdf","grobid_xml":"https://content.openalex.org/works/W4372269848.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W125553504","https://openalex.org/W1522301498","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2752782242","https://openalex.org/W2765407302","https://openalex.org/W2808631503","https://openalex.org/W2889326414","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2938358845","https://openalex.org/W2964054038","https://openalex.org/W2969985801","https://openalex.org/W2973054998","https://openalex.org/W3024869864","https://openalex.org/W3094374485","https://openalex.org/W3141035251","https://openalex.org/W3198575250","https://openalex.org/W3205335446","https://openalex.org/W4313033198","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6745136726"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"This":[0],"paper":[1],"is":[2],"concerned":[3],"with":[4,12,22,62,132],"the":[5,23,89,123,128],"task":[6],"of":[7,25],"speaker":[8,17,28,54,64,84,91,108,138],"verification":[9,18,55,85,109,139],"on":[10,121,130],"audio":[11,34,61],"multiple":[13],"overlapping":[14],"speakers.":[15],"Most":[16],"systems":[19,56],"are":[20,57],"designed":[21],"assumption":[24,42],"a":[26,32,38,73],"single":[27],"being":[29],"present":[30],"in":[31,37],"given":[33],"segment.":[35],"However,":[36],"real-world":[39],"setting":[40],"this":[41,48,68],"does":[43],"not":[44,58],"always":[45],"hold.":[46],"In":[47,97],"paper,":[49],"we":[50,70],"demonstrate":[51],"that":[52,77],"current":[53],"robust":[59,93],"against":[60,94],"noticeable":[63],"overlap.":[65],"To":[66],"alleviate":[67],"issue,":[69],"propose":[71],"margin-mixup,":[72],"simple":[74],"training":[75],"strategy":[76,126],"can":[78],"easily":[79],"be":[80],"adopted":[81],"by":[82],"existing":[83],"pipelines":[86],"to":[87,99,106,135],"make":[88],"resulting":[90],"embeddings":[92],"multi-speaker":[95,117],"audio.":[96],"contrast":[98],"other":[100],"methods,":[101],"margin-mixup":[102,125],"requires":[103],"no":[104],"alterations":[105],"regular":[107],"architectures,":[110],"while":[111],"attaining":[112],"better":[113],"results.":[114],"On":[115],"our":[116,136],"test":[118],"set":[119],"based":[120],"VoxCeleb1,":[122],"proposed":[124],"improves":[127],"EER":[129],"average":[131],"44.4%":[133],"relative":[134],"state-of-the-art":[137],"baseline":[140],"systems.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}