{"id":"https://openalex.org/W4281762205","doi":"https://doi.org/10.21437/odyssey.2022-32","title":"Deep Representation Decomposition for Rate-Invariant Speaker Verification","display_name":"Deep Representation Decomposition for Rate-Invariant Speaker Verification","publication_year":2022,"publication_date":"2022-06-17","ids":{"openalex":"https://openalex.org/W4281762205","doi":"https://doi.org/10.21437/odyssey.2022-32"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2022-32","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2022-32","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 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/A5090944758","display_name":"Fuchuan Tong","orcid":"https://orcid.org/0000-0001-5123-1843"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchuan Tong","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014586639","display_name":"Siqi Zheng","orcid":"https://orcid.org/0000-0002-4467-8505"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siqi Zheng","raw_affiliation_strings":["Speech Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010106071","display_name":"Haodong Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodong Zhou","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059413261","display_name":"Xingjia Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjia Xie","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103050255","display_name":"Lin Li","orcid":"https://orcid.org/0000-0002-5021-2648"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"228","last_page":"232"},"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":0.9983000159263611,"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":0.989300012588501,"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-verification","display_name":"Speaker verification","score":0.6641477346420288},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6107908487319946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5807275772094727},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.496039479970932},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46933048963546753},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46885594725608826},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36680060625076294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3664856553077698},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28757670521736145},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.27949631214141846}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6641477346420288},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6107908487319946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5807275772094727},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.496039479970932},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46933048963546753},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46885594725608826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36680060625076294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3664856553077698},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28757670521736145},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.27949631214141846},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2022-32","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2022-32","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 2022)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W46948191","https://openalex.org/W104572732","https://openalex.org/W1496743271","https://openalex.org/W2407080277","https://openalex.org/W2571817858","https://openalex.org/W2748466034","https://openalex.org/W2801581493","https://openalex.org/W2890964092","https://openalex.org/W2900028034","https://openalex.org/W2901368553","https://openalex.org/W2937328535","https://openalex.org/W2938358845","https://openalex.org/W2962711229","https://openalex.org/W2963767627","https://openalex.org/W2972552635","https://openalex.org/W2981087920","https://openalex.org/W2982469842","https://openalex.org/W2987269219","https://openalex.org/W3008911072","https://openalex.org/W3015443711","https://openalex.org/W3015503328","https://openalex.org/W3015555484","https://openalex.org/W3015737406","https://openalex.org/W3024869864","https://openalex.org/W3032796415","https://openalex.org/W3039280453","https://openalex.org/W3097256596","https://openalex.org/W3111060610","https://openalex.org/W3163421828","https://openalex.org/W4309845474"],"related_works":["https://openalex.org/W2376224659","https://openalex.org/W2169064893","https://openalex.org/W32484671","https://openalex.org/W4294437891","https://openalex.org/W2062195135","https://openalex.org/W1970491877","https://openalex.org/W2157090657","https://openalex.org/W2140022733","https://openalex.org/W2090976131","https://openalex.org/W1516392727"],"abstract_inverted_index":{"While":[0],"promising":[1],"performance":[2],"for":[3,126],"speaker":[4,11,30,61],"verification":[5,31],"has":[6],"been":[7],"achieved":[8],"by":[9,44],"deep":[10,50],"embeddings,":[12],"the":[13,18,37,69,83,87,100,105,109,138],"advantage":[14],"would":[15],"reduce":[16,40,82],"in":[17,28],"case":[19],"of":[20,140],"speaking-style":[21],"variability.Speaking":[22],"rate":[23,121],"mismatch":[24],"is":[25],"often":[26],"observed":[27],"practical":[29],"systems,":[32],"which":[33],"may":[34],"actually":[35],"degrade":[36],"system":[38],"performance.To":[39],"intra-class":[41],"discrepancy":[42],"caused":[43],"speaking":[45,59,120],"rate,":[46],"we":[47,67,91],"propose":[48,93],"a":[49,94,113],"representation":[51],"decomposition":[52],"approach":[53],"with":[54],"adversarial":[55],"learning":[56],"to":[57,81,98,103,119,136],"learn":[58],"rate-invariant":[60],"embeddings.Specifically,":[62],"adopting":[63],"an":[64],"attention":[65],"block,":[66],"decompose":[68],"original":[70],"embedding":[71],"into":[72],"identity-related":[73,115],"component":[74,77],"and":[75,122,133],"rate-related":[76],"through":[78],"multi-task":[79],"training.Additionally,":[80],"latent":[84],"relationship":[85],"between":[86,108],"two":[88,110],"decomposed":[89,111],"components,":[90],"further":[92],"cosine":[95,106],"mapping":[96],"block":[97],"train":[99],"parameters":[101],"adversarially":[102],"minimize":[104],"similarity":[107],"components.As":[112],"result,":[114],"features":[116],"become":[117],"robust":[118],"then":[123],"are":[124,128],"used":[125],"verification.Experiments":[127],"conducted":[129],"on":[130],"VoxCeleb1":[131],"data":[132,135],"HI-MIA":[134],"demonstrate":[137],"effectiveness":[139],"our":[141],"proposed":[142],"approach.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}