{"id":"https://openalex.org/W4375869415","doi":"https://doi.org/10.1109/icassp49357.2023.10096333","title":"Improving Transformer-Based Networks with Locality for Automatic Speaker Verification","display_name":"Improving Transformer-Based Networks with Locality for Automatic Speaker Verification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869415","doi":"https://doi.org/10.1109/icassp49357.2023.10096333"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096333","doi":"https://doi.org/10.1109/icassp49357.2023.10096333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096333","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.08639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005211900","display_name":"Mufan Sang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mufan Sang","raw_affiliation_strings":["The University of Texas, Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas, Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458721","display_name":"Yongheng Zhao","orcid":"https://orcid.org/0000-0001-5298-2833","observed_orcids":["https://orcid.org/0000-0001-5298-2833"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Zhao","raw_affiliation_strings":["Microsoft Corporation,One Microsoft Way,Redmond,WA,USA,98052"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,One Microsoft Way,Redmond,WA,USA,98052","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412456","display_name":"Gang Liu","orcid":"https://orcid.org/0000-0002-6439-3195","observed_orcids":["https://orcid.org/0000-0002-6439-3195"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Liu","raw_affiliation_strings":["Microsoft Corporation,One Microsoft Way,Redmond,WA,USA,98052"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,One Microsoft Way,Redmond,WA,USA,98052","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["The University of Texas, Dallas, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas, Dallas, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011","observed_orcids":["https://orcid.org/0000-0002-3101-7011","https://orcid.org/0009-0002-8649-3442"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Microsoft Corporation,One Microsoft Way,Redmond,WA,USA,98052"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,One Microsoft Way,Redmond,WA,USA,98052","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5351,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94422042,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"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":0.9990000128746033,"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":0.9990000128746033,"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":0.0006000000284984708,"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":9.999999747378752e-05,"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/speaker-verification","display_name":"speaker verification","score":0.9829999804496765},{"id":"https://openalex.org/keywords/speaker-embedding","display_name":"speaker embedding","score":0.8610000014305115},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.46799999475479126},{"id":"https://openalex.org/keywords/conformers","display_name":"conformational isomers","score":0.8830000162124634},{"id":"https://openalex.org/keywords/depthwise-convolution","display_name":"depthwise convolution","score":0.9240000247955322},{"id":"https://openalex.org/keywords/channel-attention","display_name":"channel attention","score":0.9950000047683716},{"id":"https://openalex.org/keywords/swin-transformer","display_name":"Swin Transformer","score":0.9940000176429749},{"id":"https://openalex.org/keywords/self-attention-limitations","display_name":"self-attention limitations","score":0.6669999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040907979011536},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7367796897888184},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7170900106430054},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6714341640472412},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5029615759849548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5002341270446777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46636685729026794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4282703101634979},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.416428804397583},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11897939443588257},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09177005290985107},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096333","doi":"https://doi.org/10.1109/icassp49357.2023.10096333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096333","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2302.08639","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.08639","pdf_url":"https://arxiv.org/pdf/2302.08639","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2302.08639","doi":"https://doi.org/10.48550/arxiv.2302.08639","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2302.08639","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.08639","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.08639","pdf_url":"https://arxiv.org/pdf/2302.08639","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375869415.pdf","grobid_xml":"https://content.openalex.org/works/W4375869415.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2752782242","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2900022717","https://openalex.org/W2908510526","https://openalex.org/W2916301830","https://openalex.org/W2962788625","https://openalex.org/W2962898354","https://openalex.org/W2963371159","https://openalex.org/W2972441390","https://openalex.org/W2972552635","https://openalex.org/W2981461916","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3047546114","https://openalex.org/W3096730275","https://openalex.org/W3097777922","https://openalex.org/W3138516171","https://openalex.org/W3142516134","https://openalex.org/W3163829335","https://openalex.org/W3206114047","https://openalex.org/W4200633018","https://openalex.org/W4205234379","https://openalex.org/W4221154745","https://openalex.org/W4225096077","https://openalex.org/W4226442948","https://openalex.org/W4296068991","https://openalex.org/W4312527085","https://openalex.org/W6688816777","https://openalex.org/W6769178842","https://openalex.org/W7208177202"],"related_works":["https://openalex.org/W4303969290","https://openalex.org/W4224916451","https://openalex.org/W4390102353","https://openalex.org/W4312527085","https://openalex.org/W3048784519","https://openalex.org/W4410465909","https://openalex.org/W3206114047","https://openalex.org/W3047941943","https://openalex.org/W4221154745","https://openalex.org/W4412923390"],"abstract_inverted_index":{"Recently,":[0],"Transformer-based":[1,131],"architectures":[2],"have":[3],"been":[4],"explored":[5],"for":[6,29,37,92],"speaker":[7,42,96],"embedding":[8,97],"extraction.":[9],"Although":[10],"the":[11,14,20,38,49,52,62,74,80,87,101,105,128,144,147,160],"Transformer":[12,50,83],"employs":[13],"self-attention":[15],"mechanism":[16],"to":[17],"efficiently":[18],"model":[19],"global":[21],"interaction":[22],"between":[23],"token":[24],"embeddings,":[25],"it":[26],"is":[27,35],"inadequate":[28],"capturing":[30],"short-range":[31],"local":[32],"context,":[33],"which":[34],"essential":[36],"accurate":[39],"extraction":[40],"of":[41],"information.":[43],"In":[44],"this":[45],"study,":[46],"we":[47,60,78],"enhance":[48],"with":[51,153],"enhanced":[53],"locality":[54],"modeling":[55],"in":[56,157],"two":[57],"directions.":[58],"First,":[59],"propose":[61],"Locality-Enhanced":[63],"Conformer":[64,75],"(LE-Confomer)":[65],"by":[66,85],"introducing":[67],"depth-wise":[68],"convolution":[69],"and":[70,108,133,139],"channel-wise":[71],"attention":[72],"into":[73,95],"blocks.":[76],"Second,":[77],"present":[79],"Speaker":[81],"Swin":[82,88],"(SST)":[84],"adapting":[86],"Transformer,":[89],"originally":[90],"proposed":[91,102,117,130,148],"vision":[93],"tasks,":[94],"network.":[98],"We":[99],"evaluate":[100],"approaches":[103],"on":[104,122,143],"VoxCeleb":[106,123],"datasets":[107],"a":[109],"large-scale":[110],"Microsoft":[111],"internal":[112],"multilingual":[113],"(MS-internal)":[114],"dataset.":[115],"The":[116],"models":[118,132,149],"achieve":[119,150],"0.75%":[120],"EER":[121,158],"1":[124],"test":[125],"set,":[126],"outperforming":[127],"previously":[129],"CNN-based":[134],"models,":[135],"such":[136],"as":[137],"ResNet34":[138],"ECAPA-TDNN.":[140],"When":[141],"trained":[142],"MS-internal":[145],"dataset,":[146],"promising":[151],"results":[152],"14.6%":[154],"relative":[155],"reduction":[156],"over":[159],"Res2Net50":[161],"model.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-05-10T00:00:00"}