{"id":"https://openalex.org/W4375798879","doi":"https://doi.org/10.1109/taslp.2023.3273417","title":"Depth-First Neural Architecture With Attentive Feature Fusion for Efficient Speaker Verification","display_name":"Depth-First Neural Architecture With Attentive Feature Fusion for Efficient Speaker Verification","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4375798879","doi":"https://doi.org/10.1109/taslp.2023.3273417"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3273417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3273417","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5114910830","display_name":"Bei Liu","orcid":"https://orcid.org/0000-0002-6208-003X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bei Liu","raw_affiliation_strings":["X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6208-003X","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyang Chen","raw_affiliation_strings":["X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1293-8146","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0314-3790","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114910830"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.2153,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89991999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"1825","last_page":"1838"},"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":0.9979000091552734,"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":0.9919000267982483,"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":0.787745475769043},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6247316002845764},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5430024266242981},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5052502751350403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48610854148864746},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48125264048576355},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.47972196340560913},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.4356004595756531},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4271145761013031},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42169439792633057},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41589146852493286},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3440197706222534},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3354441821575165},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13524076342582703},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07480776309967041}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787745475769043},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6247316002845764},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5430024266242981},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5052502751350403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48610854148864746},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48125264048576355},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.47972196340560913},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.4356004595756531},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4271145761013031},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42169439792633057},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41589146852493286},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3440197706222534},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3354441821575165},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13524076342582703},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07480776309967041},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3273417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3273417","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G5465080215","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W1589137271","https://openalex.org/W2046056978","https://openalex.org/W2150769028","https://openalex.org/W2157161740","https://openalex.org/W2194775991","https://openalex.org/W2402146185","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2752782242","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2928165649","https://openalex.org/W2936733796","https://openalex.org/W2936774411","https://openalex.org/W2938358845","https://openalex.org/W2955425717","https://openalex.org/W2962834855","https://openalex.org/W2963163009","https://openalex.org/W2963446712","https://openalex.org/W2963918968","https://openalex.org/W2964137095","https://openalex.org/W2972369255","https://openalex.org/W2972986505","https://openalex.org/W2982083293","https://openalex.org/W3010893827","https://openalex.org/W3010925296","https://openalex.org/W3015261361","https://openalex.org/W3015368919","https://openalex.org/W3024869864","https://openalex.org/W3094325190","https://openalex.org/W3094374485","https://openalex.org/W3094502228","https://openalex.org/W3094897602","https://openalex.org/W3095851346","https://openalex.org/W3095851463","https://openalex.org/W3096918678","https://openalex.org/W3097777922","https://openalex.org/W3135006803","https://openalex.org/W3141035251","https://openalex.org/W3160076723","https://openalex.org/W3177052299","https://openalex.org/W3197013563","https://openalex.org/W3197111314","https://openalex.org/W3198041020","https://openalex.org/W3198564914","https://openalex.org/W3198698812","https://openalex.org/W3206189675","https://openalex.org/W3206287456","https://openalex.org/W3209984917","https://openalex.org/W4224916451","https://openalex.org/W4224917447","https://openalex.org/W4224924217","https://openalex.org/W4226184234","https://openalex.org/W4286981691","https://openalex.org/W4288091954","https://openalex.org/W4296068762","https://openalex.org/W4297775537","https://openalex.org/W4385245566","https://openalex.org/W6713132643","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6762718338","https://openalex.org/W6769178842","https://openalex.org/W6784256521","https://openalex.org/W6784333009","https://openalex.org/W6784400926","https://openalex.org/W6784467320","https://openalex.org/W6801723603","https://openalex.org/W6810938606"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W4243305035","https://openalex.org/W2379407973","https://openalex.org/W4390846322"],"abstract_inverted_index":{"Deep":[0],"speaker":[1,14,68,100],"embedding":[2],"learning":[3],"based":[4],"on":[5,52,63,82,105,194,212,262],"neural":[6],"networks":[7,42,98],"has":[8],"become":[9],"the":[10,33,74,77,95,142,148,163,195,200,217,259],"predominant":[11],"approach":[12],"in":[13,43,147,188,233,266],"verification":[15,101],"(SV)":[16],"currently.":[17],"In":[18,58,137],"prior":[19],"studies,":[20],"researchers":[21],"have":[22],"investigated":[23],"various":[24,248],"network":[25,78],"architectures.":[26],"However,":[27],"rare":[28],"works":[29],"pay":[30],"attention":[31],"to":[32,37,47,120,139,161,229],"question":[34],"of":[35,76,97,127,144],"how":[36],"design":[38,66,115,170],"and":[39,55,80,84,122,133,179,204,214,220,264,269],"scale":[40],"up":[41,228],"a":[44,49,110,152,189,208,244],"principled":[45],"way":[46],"achieve":[48,207,258],"better":[50,210],"trade-off":[51,211,261],"model":[53],"performance":[54,83,143,213,263],"computational":[56,241],"complexity.":[57],"this":[59,106],"paper,":[60],"we":[61,71,108,169],"focus":[62],"efficient":[64],"architecture":[65,114],"for":[67,99],"verification.":[69],"Firstly,":[70],"systematically":[72],"study":[73],"effect":[75],"depth":[79],"width":[81,96],"empirically":[85],"discover":[86],"that":[87,199,254],"<italic":[88],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[89],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">depth":[90],"is":[91,159],"more":[92],"important":[93],"than":[94,216],"task</i>":[102],".":[103],"Based":[104],"observation,":[107],"propose":[109],"novel":[111,153],"depth-first":[112],"(DF)":[113],"rule.":[116],"By":[117],"applying":[118],"it":[119],"ResNet":[121,219],"ECAPA-TDNN,":[123],"two":[124,171],"new":[125],"families":[126],"much":[128,209],"deeper":[129],"models,":[130],"namely":[131],"DF-ResNets":[132,203],"DF-ECAPAs,":[134],"are":[135],"constructed.":[136],"addition,":[138],"further":[140,226],"boost":[141],"small":[145,223],"models":[146,224,257],"low":[149,268],"computation":[150,271],"regime,":[151],"attentive":[154],"feature":[155,165],"fusion":[156,166,173],"(AFF)":[157],"scheme":[158,238],"proposed":[160,202,256],"replace":[162],"conventional":[164],"methods.":[167],"Specifically,":[168],"different":[172],"strategies,":[174],"including":[175],"sequential":[176],"AFF":[177,181,237],"(S-AFF)":[178],"parallel":[180],"(P-AFF),":[182],"which":[183],"can":[184,206,225],"dynamically":[185],"fuse":[186],"features":[187],"learnable":[190],"way.":[191],"Experimental":[192],"results":[193],"VoxCeleb":[196],"dataset":[197],"show":[198],"newly":[201],"DF-ECAPAs":[205],"complexity":[215,265],"original":[218],"ECAPA-TDNN.":[221],"Moreover,":[222],"obtain":[227],"40%":[230],"relative":[231],"improvement":[232],"EER":[234],"by":[235],"adopting":[236],"with":[239,247],"negligible":[240],"cost.":[242],"Finally,":[243],"comprehensive":[245],"comparison":[246],"other":[249],"published":[250],"SV":[251],"systems":[252],"illustrates":[253],"our":[255],"best":[260],"both":[267],"high":[270],"scenarios.":[272]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}