{"id":"https://openalex.org/W4226090390","doi":"https://doi.org/10.1109/asru51503.2021.9687918","title":"MACCIF-TDNN: Multi Aspect Aggregation of Channel and Context Interdependence Features in TDNN-Based Speaker Verification","display_name":"MACCIF-TDNN: Multi Aspect Aggregation of Channel and Context Interdependence Features in TDNN-Based Speaker Verification","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4226090390","doi":"https://doi.org/10.1109/asru51503.2021.9687918"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687918","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/A5101840024","display_name":"Fangyuan Wang","orcid":"https://orcid.org/0000-0002-6482-4522"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyuan Wang","raw_affiliation_strings":["Institute of automation, Chinese Academy of Sciences,Beijing,China","Institute of automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090964459","display_name":"Zhigang Song","orcid":"https://orcid.org/0000-0002-3228-1674"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Song","raw_affiliation_strings":["Beijing University of Technology,Faculty of Information Technology,Beijing,China","Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Information Technology,Beijing,China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090555230","display_name":"Hongchen Jiang","orcid":"https://orcid.org/0000-0003-1271-7028"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongchen Jiang","raw_affiliation_strings":["Institute of automation, Chinese Academy of Sciences,Beijing,China","Institute of automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100439920","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0001-6049-8005"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of automation, Chinese Academy of Sciences,Beijing,China","Institute of automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.761,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75924214,"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":"214","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.998199999332428,"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":0.8153588771820068},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7271658182144165},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.585228681564331},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5549613833427429},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5458680391311646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.535528302192688},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4879860281944275},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.44042742252349854},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4176831543445587},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.41272130608558655},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.412431001663208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153588771820068},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7271658182144165},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.585228681564331},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5549613833427429},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5458680391311646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535528302192688},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4879860281944275},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.44042742252349854},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4176831543445587},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.41272130608558655},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.412431001663208},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9687918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687918","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":[{"id":"https://metadata.un.org/sdg/10","score":0.6800000071525574,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2752782242","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2964054038","https://openalex.org/W2969985801","https://openalex.org/W2972369255","https://openalex.org/W2972609576","https://openalex.org/W3010925296","https://openalex.org/W3016112863","https://openalex.org/W3024869864","https://openalex.org/W3048784519","https://openalex.org/W3095992690","https://openalex.org/W3141035251","https://openalex.org/W4288091954","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6740167877","https://openalex.org/W6742911084"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W3103989898","https://openalex.org/W4287804464","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"Most":[0],"of":[1,62,92,121,141,176],"the":[2,28,47,55,89,96,114,119,128,155,177],"recent":[3],"state-of-the-art":[4,178],"results":[5],"for":[6],"speaker":[7],"verification":[8],"are":[9],"achieved":[10],"by":[11,136],"X-vector":[12],"and":[13,30,65,123,131],"its":[14],"subsequent":[15],"variants.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20,45,85,117,148],"propose":[21],"a":[22,71,75,143,159],"new":[23],"network":[24],"architecture":[25,172],"which":[26,105,162],"aggregates":[27],"channel":[29,56,63,130],"context":[31,68,98,132],"interdependence":[32,57,99,133],"features":[33,69,100,134,165],"from":[34,166],"multi":[35],"aspects":[36],"based":[37,180],"on":[38,182],"Time":[39],"Delay":[40],"Neural":[41],"Network":[42],"(TDNN).":[43],"Firstly,":[44],"use":[46,88],"SE-Res2Blocks":[48,122],"as":[49],"in":[50,70,158],"ECAPA-TDNN":[51],"to":[52,58,87,94,126,153],"explicitly":[53],"model":[54,95],"realize":[59],"adaptive":[60],"calibration":[61],"features,":[64],"process":[66],"local":[67],"multi-scale":[72],"way":[73,161],"at":[74,101],"more":[76],"granular":[77],"level":[78,104],"compared":[79],"with":[80],"conventional":[81],"TDNN-based":[82],"methods.":[83],"Secondly,":[84],"explore":[86],"encoder":[90],"structure":[91],"Transformer":[93,124],"global":[97],"an":[102],"utterance":[103],"can":[106,163,173],"capture":[107],"better":[108],"long":[109],"term":[110],"temporal":[111],"characteristics.":[112],"Before":[113],"pooling":[115,156],"layer,":[116],"aggregate":[118],"outputs":[120],"Encoders":[125],"leverage":[127],"complementary":[129],"learned":[135],"themself":[137],"respectively.":[138],"Finally,":[139],"instead":[140],"performing":[142],"single":[144],"attentive":[145],"statistics":[146],"pooling,":[147],"also":[149],"find":[150],"it":[151],"beneficial":[152],"extend":[154],"method":[157],"multi-head":[160],"discriminate":[164],"multiple":[167],"aspects.":[168],"The":[169],"proposed":[170],"MACCIF-TDNN":[171],"outperform":[174],"most":[175],"TDNN":[179],"systems":[181],"VoxCeleb1":[183],"test":[184],"sets.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}