{"id":"https://openalex.org/W4408345767","doi":"https://doi.org/10.1109/icassp49660.2025.10890585","title":"Efficient Extreme Large-Scale Speaker Verification: Dynamic Active Sub Fully-Connected Layers for Faster Training and Memory Optimization","display_name":"Efficient Extreme Large-Scale Speaker Verification: Dynamic Active Sub Fully-Connected Layers for Faster Training and Memory Optimization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345767","doi":"https://doi.org/10.1109/icassp49660.2025.10890585"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5056847336","display_name":"Fulin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fulin Zhang","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018560999","display_name":"Chenguang Hu","orcid":"https://orcid.org/0000-0003-1880-5520"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenguang Hu","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101413555","display_name":"Yao Shen","orcid":"https://orcid.org/0009-0005-8603-2314"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Shen","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508981","display_name":"Yingying Gao","orcid":"https://orcid.org/0000-0002-7020-3028"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Gao","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618830","display_name":"Shilei Zhang","orcid":"https://orcid.org/0009-0007-5182-3065"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilei Zhang","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079750750","display_name":"Junlan Feng","orcid":"https://orcid.org/0000-0001-5292-2945"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlan Feng","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180662265"],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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":0.9976999759674072,"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":0.996399998664856,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9437000155448914,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7919131517410278},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7063226103782654},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5671995282173157},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4791561961174011},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.346631795167923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.30001306533813477},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2478393316268921}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919131517410278},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7063226103782654},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5671995282173157},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4791561961174011},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.346631795167923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30001306533813477},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2478393316268921},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W2100714283","https://openalex.org/W2157161740","https://openalex.org/W2194775991","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2963355595","https://openalex.org/W2969985801","https://openalex.org/W3010893827","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3094374485","https://openalex.org/W3157066609","https://openalex.org/W3169862551","https://openalex.org/W3174971746","https://openalex.org/W3205519288","https://openalex.org/W3206189675","https://openalex.org/W3206886023","https://openalex.org/W3217435001","https://openalex.org/W4206550256","https://openalex.org/W4206908380","https://openalex.org/W4221154745","https://openalex.org/W4312622571","https://openalex.org/W4312769845","https://openalex.org/W4313166084","https://openalex.org/W4385822315","https://openalex.org/W4385822503","https://openalex.org/W6619292343","https://openalex.org/W6688816777","https://openalex.org/W6784256521","https://openalex.org/W6801723603"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2140022733","https://openalex.org/W2090976131","https://openalex.org/W1516392727"],"abstract_inverted_index":{"Using":[0],"larger":[1],"scale":[2],"datasets":[3],"in":[4,153],"the":[5,19,23,34,49],"training":[6,24,35,140],"stage":[7],"of":[8,22,53,83],"speaker":[9,20,78,97,108],"verification":[10],"model":[11,100,154],"usually":[12],"leads":[13],"to":[14,67,96,111,130,138],"better":[15],"performance.":[16,155],"However,":[17],"when":[18],"number":[21],"dataset":[25,123],"becomes":[26],"extreme":[27,50,121],"large":[28,51,122],"(e.g.,":[29],"more":[30],"than":[31],"1":[32],"million),":[33],"speed":[36],"and":[37,107,115,142],"GPU":[38,145],"memory":[39,146],"demand":[40],"will":[41],"become":[42],"bottlenecks":[43],"which":[44],"are":[45,74,93],"mainly":[46],"brought":[47],"by":[48,80],"dimension":[52],"last":[54,84],"fully-connected(FC)":[55],"layer\u2019s":[56,86],"weight":[57,87],"matrix.":[58,88],"We":[59,102],"propose":[60],"dynamic":[61],"active":[62],"sub":[63,90],"FC":[64,85,91,132],"layers":[65,92],"(DAS-FC)":[66],"tackle":[68],"this":[69],"problem.":[70],"Firstly,":[71],"all":[72],"speakers":[73,126],"dynamically":[75],"divided":[76],"into":[77],"groups":[79,98],"clustering":[81],"rows":[82],"Then,":[89],"generated":[94],"according":[95],"for":[99],"training.":[101],"also":[103],"introduce":[104],"Mini-Batch":[105],"K-means":[106],"based":[109],"dataloader":[110],"further":[112],"reduce":[113],"time":[114,141],"resource":[116],"costing.":[117],"Experiments":[118],"on":[119],"an":[120],"with":[124,148],"1,068,237":[125],"show":[127],"that":[128],"compared":[129],"traditional":[131],"layer,":[133],"DAS-FC":[134],"can":[135],"save":[136,143],"up":[137],"87%":[139],"56%":[144],"occupancy":[147],"only":[149],"a":[150],"4.2%":[151],"drop":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}