{"id":"https://openalex.org/W4224916451","doi":"https://doi.org/10.1109/icassp43922.2022.9746050","title":"Local Information Modeling with Self-Attention for Speaker Verification","display_name":"Local Information Modeling with Self-Attention for Speaker Verification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224916451","doi":"https://doi.org/10.1109/icassp43922.2022.9746050"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746050","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":"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/A5100690517","display_name":"Bing Han","orcid":"https://orcid.org/0000-0002-6319-6755"},"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":"Bing Han","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, 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":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, 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":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6727","last_page":"6731"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8343026041984558},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.701900064945221},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.47258150577545166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45852839946746826},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.431276798248291},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4250478744506836},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42114678025245667},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4182548224925995},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4144074320793152},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4090091586112976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40583571791648865},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40095826983451843},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10089582204818726},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08747580647468567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8343026041984558},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.701900064945221},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.47258150577545166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45852839946746826},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.431276798248291},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4250478744506836},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42114678025245667},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4182548224925995},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4144074320793152},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4090091586112976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40583571791648865},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40095826983451843},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10089582204818726},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08747580647468567},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746050","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W1589137271","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2896457183","https://openalex.org/W2905016804","https://openalex.org/W2946200149","https://openalex.org/W2964189376","https://openalex.org/W3004720752","https://openalex.org/W3010893827","https://openalex.org/W3016129867","https://openalex.org/W3024869864","https://openalex.org/W3094502228","https://openalex.org/W3095201711","https://openalex.org/W3096918678","https://openalex.org/W3097777922","https://openalex.org/W3104056985","https://openalex.org/W3197181902","https://openalex.org/W3197242296","https://openalex.org/W4288091954","https://openalex.org/W4385245566","https://openalex.org/W6635152626","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6744649695","https://openalex.org/W6755207826","https://openalex.org/W6763832098","https://openalex.org/W6769178842","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6784784087"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287598411","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W3094871513","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"Transformer":[0],"based":[1],"on":[2,47,110],"self":[3],"attention":[4,97],"mechanism":[5],"has":[6],"demonstrated":[7],"its":[8],"state-of-the-art":[9],"performance":[10],"in":[11,28,82],"most":[12],"natural":[13],"language":[14],"processing":[15],"(NLP)":[16],"tasks,":[17],"but":[18,71],"it\u2019s":[19],"not":[20],"very":[21],"competitive":[22],"when":[23],"applied":[24],"for":[25,128],"speaker":[26,32,129],"verification":[27,130],"previous":[29],"works.":[30],"Generally,":[31],"identity":[33],"is":[34],"mostly":[35],"reflected":[36],"by":[37],"the":[38,52,56,63,75,87,96,123],"relationship":[39],"between":[40],"adjacent":[41],"tokens,":[42],"whose":[43],"extraction":[44],"mainly":[45],"depends":[46],"local":[48,76,88,101,126],"modeling":[49,90],"ability.":[50],"However,":[51],"self-attention":[53],"module,":[54],"as":[55],"key":[57],"component":[58],"of":[59,68,125],"transformer,":[60],"can":[61,117],"help":[62],"model":[64],"make":[65],"full":[66],"use":[67],"global":[69],"information":[70,89,127],"insufficient":[72],"to":[73,99],"capture":[74],"information.":[77],"To":[78],"tackle":[79],"this":[80,83],"limitation,":[81],"paper,":[84],"we":[85],"strengthen":[86],"from":[91],"two":[92],"different":[93],"aspects:":[94],"restricting":[95],"context":[98],"be":[100],"and":[102],"introducing":[103],"convolution":[104],"operation":[105],"into":[106],"transformer.":[107],"Experiments":[108],"conducted":[109],"Voxceleb":[111],"illustrate":[112],"that":[113],"our":[114],"proposed":[115],"methods":[116],"notably":[118],"improve":[119],"system":[120],"performance,":[121],"verifying":[122],"significance":[124],"task.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}