{"id":"https://openalex.org/W3163421828","doi":"https://doi.org/10.1109/icassp39728.2021.9414676","title":"ASV-SUBTOOLS: Open Source Toolkit for Automatic Speaker Verification","display_name":"ASV-SUBTOOLS: Open Source Toolkit for Automatic Speaker Verification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163421828","doi":"https://doi.org/10.1109/icassp39728.2021.9414676","mag":"3163421828"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5074355807","display_name":"Miao Zhao","orcid":"https://orcid.org/0000-0002-4324-1467"},"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":"Miao Zhao","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":"middle","author":{"id":"https://openalex.org/A5101544207","display_name":"Jianfeng Zhou","orcid":"https://orcid.org/0000-0001-5093-773X"},"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":"Jianfeng 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/A5101764009","display_name":"Hao Lu","orcid":"https://orcid.org/0000-0002-9283-0209"},"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":"Hao Lu","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":"middle","author":{"id":"https://openalex.org/A5100414996","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0002-3938-7033"},"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":"Zheng 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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"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"]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6184","last_page":"6188"},"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":0.9987999796867371,"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":0.9958000183105469,"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":0.868474006652832},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6209922432899475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5519235134124756},{"id":"https://openalex.org/keywords/modularity","display_name":"Modularity (biology)","score":0.5393748879432678},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5191102027893066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49866676330566406},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42090895771980286},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4118378758430481},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34878009557724},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33118587732315063},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.28864291310310364},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13647639751434326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.868474006652832},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6209922432899475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5519235134124756},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.5393748879432678},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5191102027893066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49866676330566406},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42090895771980286},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4118378758430481},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34878009557724},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33118587732315063},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.28864291310310364},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13647639751434326},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2095705004","https://openalex.org/W2399762392","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2888867175","https://openalex.org/W2888968865","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2938358845","https://openalex.org/W2939762919","https://openalex.org/W2949526695","https://openalex.org/W2963371159","https://openalex.org/W2963446838","https://openalex.org/W2969985801","https://openalex.org/W2972369255","https://openalex.org/W2972552635","https://openalex.org/W2972986505","https://openalex.org/W3015231328","https://openalex.org/W3015546017","https://openalex.org/W3024869864","https://openalex.org/W3103152812","https://openalex.org/W6674330103","https://openalex.org/W6749813370","https://openalex.org/W6750372021","https://openalex.org/W6777437564"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"In":[0,59],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"a":[5],"new":[6],"open":[7],"source":[8],"toolkit":[9,26,42],"for":[10,27,101,106],"automatic":[11],"speaker":[12,36,57,102],"verification":[13],"(ASV),":[14],"named":[15,91],"ASV-Subtools.":[16],"Adopting":[17],"PyTorch":[18],"as":[19,68],"main":[20],"deep":[21],"learning":[22],"engine":[23],"and":[24,39,46,78,113],"Kaldi":[25],"data":[28,88],"processing,":[29],"ASV-Subtools":[30,80,116,136],"allows":[31],"users":[32],"to":[33,61,142],"develop":[34],"modern":[35],"recognizers":[37],"flexibly":[38],"efficiently.":[40],"The":[41],"prioritizes":[43],"efficiency,":[44],"modularity,":[45],"extensibility":[47],"with":[48,94],"the":[49,53,63,69,108],"goal":[50],"of":[51,86,122],"supporting":[52],"state-of-the-art":[54,132],"technologies":[55],"in":[56],"recognition.":[58],"addition":[60],"including":[62],"commonly":[64],"used":[65],"networks,":[66],"such":[67],"time":[70],"delay":[71],"neural":[72],"networks":[73],"(TDNN),":[74],"factorized":[75],"TDNN":[76],"(F-TDNN)":[77],"ResNet,":[79],"also":[81],"integrates":[82],"an":[83],"upgraded":[84],"version":[85],"SpecAugment":[87],"augmentation":[89],"method,":[90],"Inverted":[92],"SpecAugment,":[93],"focus":[95],"on":[96,135],"making":[97],"it":[98],"more":[99],"appropriate":[100],"recognition":[103],"subtasks.":[104],"Besides,":[105],"alleviating":[107],"domain":[109,119],"mismatch":[110],"between":[111],"training":[112],"test":[114],"data,":[115],"provides":[117],"multiple":[118],"adaptation":[120],"methods":[121],"Probabilistic":[123],"Linear":[124],"Discriminant":[125],"Analysis":[126],"(PLDA).":[127],"Experimental":[128],"results":[129],"show":[130],"that":[131],"techniques":[133],"implemented":[134],"could":[137],"achieve":[138],"competitive":[139],"performance":[140],"compared":[141],"other":[143],"implementations.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
