{"id":"https://openalex.org/W4225276605","doi":"https://doi.org/10.1109/icassp43922.2022.9746956","title":"Robust Speaker Verification Using Population-Based Data Augmentation","display_name":"Robust Speaker Verification Using Population-Based Data Augmentation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225276605","doi":"https://doi.org/10.1109/icassp43922.2022.9746956"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746956","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5090644975","display_name":"Weiwei Lin","orcid":"https://orcid.org/0000-0002-9241-0271"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Weiwei Lin","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electronic and Information Engineering,Hong Kong SAR","Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electronic and Information Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electronic and Information Engineering,Hong Kong SAR","Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electronic and Information Engineering,Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090644975"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":1.5591,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8470696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9998999834060669,"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":0.9994000196456909,"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":0.8430574536323547},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.634963870048523},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6181545853614807},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.597944974899292},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5851178169250488},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5810233354568481},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5770154595375061},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5236154198646545},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4875602126121521},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48154667019844055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4725888669490814},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4480920433998108},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4345102906227112},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39892956614494324},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36245229840278625},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13841840624809265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8430574536323547},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.634963870048523},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6181545853614807},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.597944974899292},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5851178169250488},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5810233354568481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5770154595375061},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5236154198646545},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4875602126121521},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48154667019844055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4725888669490814},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4480920433998108},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4345102906227112},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39892956614494324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36245229840278625},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13841840624809265},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746956","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2888955371","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2952217990","https://openalex.org/W2963040451","https://openalex.org/W2972392008","https://openalex.org/W2973147881","https://openalex.org/W3015964387","https://openalex.org/W3024200162","https://openalex.org/W3035682985","https://openalex.org/W3096127734","https://openalex.org/W4295727797","https://openalex.org/W4394662461","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6751795773","https://openalex.org/W6762619590","https://openalex.org/W6863618527"],"related_works":["https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W2134501921","https://openalex.org/W3048257020","https://openalex.org/W204267554","https://openalex.org/W2147062549","https://openalex.org/W4252590334","https://openalex.org/W4317103504","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Speaker":[0],"recognition":[1,31],"under":[2],"environments":[3,27],"with":[4],"a":[5,29,56,78,85,94,108],"low":[6],"signal-to-noise":[7],"ratio":[8],"(SNR)":[9],"and":[10],"high":[11],"reverberation":[12],"level":[13],"has":[14,49],"always":[15],"been":[16],"challenging.":[17],"Data":[18],"augmentation":[19,37,63,70,73,105],"can":[20],"be":[21],"applied":[22],"to":[23,67],"simulate":[24],"the":[25,36,62,68,89,99,123],"adverse":[26],"that":[28],"speaker":[30],"system":[32],"may":[33],"encounter.":[34],"Typically,":[35],"parameters":[38],"are":[39],"manually":[40],"set.":[41,126],"Recently,":[42],"automatic":[43],"hyper-parameter":[44],"optimization":[45],"using":[46,107],"population-based":[47,57,72],"learning":[48],"shown":[50],"promising":[51],"results.":[52],"This":[53,91],"paper":[54],"proposes":[55],"searching":[58],"strategy":[59,92],"for":[60,87],"optimizing":[61],"parameters.":[64],"We":[65,102],"refer":[66],"resulting":[69],"as":[71],"(PBA).":[74],"Instead":[75],"of":[76,81,110,120],"finding":[77],"fixed":[79],"set":[80],"hyper-parameters,":[82],"PBA":[83],"learns":[84],"scheduler":[86],"setting":[88],"hyper-parameters.":[90],"offers":[93],"considerable":[95],"computation":[96],"advantage":[97],"over":[98],"grid":[100],"search.":[101],"obtained":[103],"high-performance":[104],"policies":[106],"population":[109],"six":[111],"networks":[112],"only.":[113],"With":[114],"PBA,":[115],"we":[116],"achieved":[117],"an":[118],"EER":[119],"3.98%":[121],"on":[122],"VOiCES19":[124],"evaluation":[125]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}