{"id":"https://openalex.org/W4225789456","doi":"https://doi.org/10.1109/asru51503.2021.9688017","title":"SpeechNAS: Towards Better Trade-Off Between Latency and Accuracy for Large-Scale Speaker Verification","display_name":"SpeechNAS: Towards Better Trade-Off Between Latency and Accuracy for Large-Scale Speaker Verification","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4225789456","doi":"https://doi.org/10.1109/asru51503.2021.9688017"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688017","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5102145987","display_name":"Yuan Xu","orcid":"https://orcid.org/0000-0002-5483-0259"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":true,"raw_author_name":"Wentao Zhu","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066740027","display_name":"Tianlong Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Tianlong Kong","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004928583","display_name":"Shun L\u00fc","orcid":"https://orcid.org/0000-0001-8833-7262"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Shun Lu","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101688118","display_name":"Jixiang Li","orcid":"https://orcid.org/0000-0001-5949-1498"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jixiang Li","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379743","display_name":"Dawei Zhang","orcid":"https://orcid.org/0000-0002-0841-7826"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Dawei Zhang","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021569445","display_name":"Feng Deng","orcid":"https://orcid.org/0000-0002-1381-0243"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Deng","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002854172","display_name":"Sen Yang","orcid":"https://orcid.org/0000-0003-3222-2268"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Sen Yang","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396318","display_name":"Ji Liu","orcid":"https://orcid.org/0000-0002-0240-8881"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ji Liu","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5102145987"],"corresponding_institution_ids":["https://openalex.org/I4401726859"],"apc_list":null,"apc_paid":null,"fwci":0.7613,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75896488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1102","last_page":"1109"},"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":0.9983999729156494,"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":0.9973000288009644,"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":0.7565265893936157},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.7195449471473694},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6884099245071411},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5736088752746582},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5530329346656799},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5047804117202759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4847642779350281},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4355087876319885},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.4295922517776489},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17921710014343262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7565265893936157},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.7195449471473694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6884099245071411},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5736088752746582},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5530329346656799},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5047804117202759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4847642779350281},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4355087876319885},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.4295922517776489},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17921710014343262}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688017","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":63,"referenced_works":["https://openalex.org/W202805564","https://openalex.org/W1524333225","https://openalex.org/W2121750345","https://openalex.org/W2150769028","https://openalex.org/W2159736522","https://openalex.org/W2192203593","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2752782242","https://openalex.org/W2808631503","https://openalex.org/W2888897023","https://openalex.org/W2888968865","https://openalex.org/W2889052710","https://openalex.org/W2889385246","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2928165649","https://openalex.org/W2936774411","https://openalex.org/W2938358845","https://openalex.org/W2939634425","https://openalex.org/W2951104886","https://openalex.org/W2952587893","https://openalex.org/W2962788625","https://openalex.org/W2962850830","https://openalex.org/W2963224870","https://openalex.org/W2964154960","https://openalex.org/W2972961496","https://openalex.org/W2972986505","https://openalex.org/W2994749257","https://openalex.org/W2999547272","https://openalex.org/W3006741730","https://openalex.org/W3006876715","https://openalex.org/W3007327651","https://openalex.org/W3007460537","https://openalex.org/W3007997916","https://openalex.org/W3008104819","https://openalex.org/W3008230514","https://openalex.org/W3008712156","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3094918968","https://openalex.org/W3095476325","https://openalex.org/W3095851463","https://openalex.org/W3096025930","https://openalex.org/W3096533519","https://openalex.org/W3097244734","https://openalex.org/W3098926221","https://openalex.org/W3115471746","https://openalex.org/W3137288819","https://openalex.org/W3167899070","https://openalex.org/W6608206471","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6698200468","https://openalex.org/W6740167877","https://openalex.org/W6751593755","https://openalex.org/W6752515464","https://openalex.org/W6761158446","https://openalex.org/W6761176859","https://openalex.org/W6767064347","https://openalex.org/W6791675327"],"related_works":["https://openalex.org/W2743258233","https://openalex.org/W4307834408","https://openalex.org/W4320925816","https://openalex.org/W3208883981","https://openalex.org/W2997969508","https://openalex.org/W4214883769","https://openalex.org/W2921182884","https://openalex.org/W3202370288","https://openalex.org/W2794558692","https://openalex.org/W3142820373"],"abstract_inverted_index":{"Recently,":[0],"x-vector":[1,35],"[1]":[2],"has":[3,36],"been":[4,37,47],"a":[5,15,80,116,174],"successful":[6],"and":[7,21,42,63,108,136],"popular":[8],"approach":[9],"for":[10],"speaker":[11,26,98,142],"verification,":[12],"which":[13,166],"employs":[14],"time":[16],"delay":[17],"neural":[18,44,86,149],"network":[19,125,150],"(TDNN)":[20],"statistics":[22,103],"pooling":[23],"to":[24,74,129],"extract":[25],"characterizing":[27],"embedding":[28],"from":[29,79,127],"variable-length":[30],"utterances.":[31],"Improvement":[32],"upon":[33],"the":[34,52,76,93,97,139,160],"an":[38,152],"active":[39],"research":[40],"area,":[41],"enormous":[43],"networks":[45],"have":[46],"elaborately":[48],"designed":[49],"based":[50,82,170],"on":[51,138,159],"x-vector,":[53],"e.g.,":[54],"extended":[55],"TDNN":[56,60,66,81,169],"(E-TDNN)":[57],"[2],":[58],"factorized":[59],"(F-TDNN)":[61],"[3],":[62],"densely":[64],"connected":[65],"(D-TDNN)":[67],"[4].":[68],"In":[69],"this":[70],"work,":[71],"we":[72],"try":[73],"identify":[75],"optimal":[77],"architectures":[78],"search":[83,88],"space":[84],"employing":[85],"architecture":[87],"(NAS),":[89],"named":[90],"SpeechNAS.":[91],"Leveraging":[92],"recent":[94],"advances":[95],"in":[96],"recognition,":[99],"such":[100],"as":[101],"high-order":[102],"pooling,":[104],"multi-branch":[105],"mechanism,":[106],"D-TDNN":[107],"angular":[109],"additive":[110],"margin":[111],"softmax":[112],"(AAM)":[113],"loss":[114],"with":[115],"minimum":[117],"hyper-spherical":[118],"energy":[119],"(MHE),":[120],"SpeechNAS":[121],"automatically":[122],"discovers":[123],"five":[124],"architectures,":[126],"SpeechNAS-1":[128],"SpeechNAS-5,":[130],"of":[131,134,157,164],"various":[132],"numbers":[133],"parameters":[135],"GFLOPs":[137],"large-scale":[140],"text-independent":[141],"recognition":[143],"dataset":[144],"VoxCelebl.":[145],"Our":[146],"derived":[147],"best":[148],"achieves":[151],"equal":[153],"error":[154],"rate":[155],"(EER)":[156],"1.02%":[158],"standard":[161],"test":[162],"set":[163],"VoxCelebl,":[165],"surpasses":[167],"previous":[168],"state-of-the-art":[171],"approaches":[172],"by":[173],"large":[175],"margin.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}