{"id":"https://openalex.org/W4402116008","doi":"https://doi.org/10.21437/interspeech.2024-700","title":"A Joint Noise Disentanglement and Adversarial Training Framework for Robust Speaker Verification","display_name":"A Joint Noise Disentanglement and Adversarial Training Framework for Robust Speaker Verification","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402116008","doi":"https://doi.org/10.21437/interspeech.2024-700"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-700","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.11562","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111310998","display_name":"Xujiang Xing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xujiang Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111983309","display_name":"Mingxing Xu","orcid":"https://orcid.org/0009-0000-3878-315X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxing Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"707","last_page":"711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9857000112533569,"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":0.9617999792098999,"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":0.7622754573822021},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7581976056098938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7353267669677734},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7119570970535278},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6368781328201294},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5391491055488586},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5270571708679199},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.518523097038269},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.48657166957855225},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4713327884674072},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4702666699886322},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4547816812992096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36806291341781616},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3227171301841736},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17319339513778687},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1205536425113678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622754573822021},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7581976056098938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7353267669677734},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7119570970535278},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6368781328201294},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5391491055488586},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5270571708679199},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.518523097038269},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.48657166957855225},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4713327884674072},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4702666699886322},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4547816812992096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36806291341781616},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3227171301841736},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17319339513778687},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1205536425113678},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-700","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.11562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.11562","pdf_url":"https://arxiv.org/pdf/2408.11562","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.11562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.11562","pdf_url":"https://arxiv.org/pdf/2408.11562","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402116008.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W3141593045","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Automatic":[0],"Speaker":[1],"Verification":[2],"(ASV)":[3],"suffers":[4],"from":[5,91],"performance":[6,112],"degradation":[7],"in":[8],"noisy":[9,122],"conditions.":[10,123],"To":[11],"address":[12],"this":[13],"issue,":[14],"we":[15],"propose":[16],"a":[17,27,53,98],"novel":[18],"adversarial":[19,82],"learning":[20],"framework":[21],"that":[22,106],"incorporates":[23],"noise-disentanglement":[24],"to":[25,56,66,71,86],"establish":[26],"noise-independent":[28,73],"speaker":[29,42,69,74,78,89,115],"invariant":[30],"embedding":[31,100],"space.":[32,101],"Specifically,":[33],"the":[34,58,68,88,107,111,114],"disentanglement":[35],"module":[36,50],"includes":[37],"two":[38],"encoders":[39],"for":[40,96],"separating":[41],"related":[43],"and":[44,121],"irrelevant":[45],"information,":[46],"respectively.":[47],"The":[48],"reconstruction":[49],"serves":[51],"as":[52],"regularization":[54],"term":[55],"constrain":[57],"noise.":[59],"A":[60],"feature-robust":[61],"loss":[62],"is":[63,84],"also":[64],"used":[65],"supervise":[67],"encoder":[70,90],"learn":[72],"embeddings":[75],"without":[76],"losing":[77],"information.":[79],"In":[80],"addition,":[81],"training":[83],"introduced":[85],"discourage":[87],"encoding":[92],"acoustic":[93],"condition":[94],"information":[95],"achieving":[97],"speaker-invariant":[99],"Experiments":[102],"on":[103],"VoxCeleb1":[104],"indicate":[105],"proposed":[108],"method":[109],"improves":[110],"of":[113],"verification":[116],"system":[117],"under":[118],"both":[119],"clean":[120]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}