{"id":"https://openalex.org/W3198777143","doi":"https://doi.org/10.21437/interspeech.2021-405","title":"Improved Meta-Learning Training for Speaker Verification","display_name":"Improved Meta-Learning Training for Speaker Verification","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198777143","doi":"https://doi.org/10.21437/interspeech.2021-405","mag":"3198777143"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-405","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5003578886","display_name":"Yafeng Chen","orcid":"https://orcid.org/0000-0002-5459-4428"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafeng Chen","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101085190","display_name":"Wu Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101875578","display_name":"Bin Gu","orcid":"https://orcid.org/0000-0003-1621-7311"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Gu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1049","last_page":"1053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9941999912261963,"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/T10860","display_name":"Speech and Audio Processing","score":0.9915000200271606,"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":0.7926872968673706},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6699527502059937},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5511155724525452},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5275660753250122},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5120342373847961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5070700645446777},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.44954273104667664},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4330669045448303},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4274272918701172},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.41906508803367615},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41196149587631226},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3742958605289459},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37193405628204346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926872968673706},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6699527502059937},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5511155724525452},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5275660753250122},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5120342373847961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5070700645446777},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.44954273104667664},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4330669045448303},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4274272918701172},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.41906508803367615},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41196149587631226},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3742958605289459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37193405628204346},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-405","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G6450856609","display_name":null,"funder_award_id":"U1836219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2271840356","https://openalex.org/W2395750323","https://openalex.org/W2516764878","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2963386851","https://openalex.org/W2963418523","https://openalex.org/W2964351684","https://openalex.org/W2998508940","https://openalex.org/W3005680577","https://openalex.org/W3009561768","https://openalex.org/W3015574842","https://openalex.org/W3035524453","https://openalex.org/W3096235116","https://openalex.org/W4288558760"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W1996621592","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Meta-learning":[0],"(ML)":[1],"has":[2],"recently":[3],"become":[4],"a":[5,28,102],"research":[6],"hotspot":[7],"in":[8,22,52,76,94,118,127],"speaker":[9,49],"verification":[10],"(SV).We":[11],"introduce":[12],"two":[13,148,157],"methods":[14,136],"to":[15,69,90,97,115],"improve":[16],"the":[17,25,37,62,71,77,81,106,109,116,125,128,135],"meta-learning":[18,143],"training":[19,51,144],"for":[20],"SV":[21],"this":[23],"paper.For":[24],"first":[26,33],"method,":[27],"backbone":[29,73],"embedding":[30,74],"network":[31,75],"is":[32,88,113],"jointly":[34],"trained":[35,59],"with":[36,60],"conventional":[38],"cross":[39],"entropy":[40],"loss":[41,104],"and":[42,101,108,131],"prototypical":[43],"networks":[44],"(PN)":[45],"loss.Then,":[46],"inspired":[47],"by":[48],"adaptive":[50],"speech":[53],"recognition,":[54],"additional":[55],"transformation":[56,65],"coefficients":[57,66],"are":[58,67,121],"only":[61],"PN":[63],"loss.The":[64],"used":[68],"modify":[70],"original":[72,110],"x-vector":[78],"extraction":[79],"process.Furthermore,":[80],"random":[82],"erasing":[83],"(RE)":[84],"data":[85],"augmentation":[86],"technique":[87],"applied":[89],"all":[91],"support":[92,111],"samples":[93,112],"each":[95],"episode":[96],"construct":[98],"positive":[99],"pairs,":[100],"contrastive":[103],"between":[105],"augmented":[107],"added":[114],"objective":[117],"model":[119],"training.Experiments":[120],"carried":[122],"out":[123],"on":[124,155],"Speaker":[126],"Wild":[129],"(SITW)":[130],"VOiCES":[132],"databases.Both":[133],"of":[134],"can":[137,151],"obtain":[138],"consistent":[139],"improvements":[140,154],"over":[141],"existing":[142],"frameworks.By":[145],"combining":[146],"these":[147,156],"methods,":[149],"we":[150],"observe":[152],"further":[153],"databases.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}