{"id":"https://openalex.org/W3048825472","doi":"https://doi.org/10.1109/slt48900.2021.9383565","title":"Cross Attentive Pooling for Speaker Verification","display_name":"Cross Attentive Pooling for Speaker Verification","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3048825472","doi":"https://doi.org/10.1109/slt48900.2021.9383565","mag":"3048825472"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.05983","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043877199","display_name":"Seong Min Kye","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seong Min Kye","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology","Naver Corporation","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Naver Corporation","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019238472","display_name":"Yoohwan Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]},{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoohwan Kwon","raw_affiliation_strings":["Naver Corporation","Yonsei University","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Corporation","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Naver Corporation","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Corporation","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043877199"],"corresponding_institution_ids":["https://openalex.org/I157485424","https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":0.42331073,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66347126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"294","last_page":"300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/pooling","display_name":"Pooling","score":0.9166867136955261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7857793569564819},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7770446538925171},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6822996735572815},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6446363925933838},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6242402791976929},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5824794173240662},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5659918189048767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5262852311134338},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45205777883529663},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4285414218902588},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3743405342102051},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3379708528518677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09369313716888428}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9166867136955261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857793569564819},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7770446538925171},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6822996735572815},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6446363925933838},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6242402791976929},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5824794173240662},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5659918189048767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5262852311134338},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45205777883529663},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4285414218902588},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3743405342102051},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3379708528518677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09369313716888428},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.05983","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.05983","pdf_url":"https://arxiv.org/pdf/2008.05983","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:3048825472","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.05983.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.05983","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.05983","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/zpd7-td25","is_oa":true,"landing_page_url":"https://doi.org/10.17023/zpd7-td25","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.05983","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.05983","pdf_url":"https://arxiv.org/pdf/2008.05983","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2114925438","https://openalex.org/W2194775991","https://openalex.org/W2502312327","https://openalex.org/W2601450892","https://openalex.org/W2726515241","https://openalex.org/W2746742816","https://openalex.org/W2748488820","https://openalex.org/W2766191375","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2884412522","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2939763029","https://openalex.org/W2940070181","https://openalex.org/W2951758756","https://openalex.org/W2962898354","https://openalex.org/W2962959915","https://openalex.org/W2963040451","https://openalex.org/W2963173190","https://openalex.org/W2963371159","https://openalex.org/W2963386851","https://openalex.org/W2969985801","https://openalex.org/W2970971581","https://openalex.org/W2971035910","https://openalex.org/W2972986505","https://openalex.org/W2973032144","https://openalex.org/W2981087920","https://openalex.org/W2981461916","https://openalex.org/W2991951409","https://openalex.org/W3010925296","https://openalex.org/W3013020904","https://openalex.org/W3014217528","https://openalex.org/W3020953549","https://openalex.org/W3044308976","https://openalex.org/W3096235116","https://openalex.org/W3097256596","https://openalex.org/W3103152812","https://openalex.org/W6648737282","https://openalex.org/W6724804524","https://openalex.org/W6735236233","https://openalex.org/W6753575415","https://openalex.org/W6761233929","https://openalex.org/W6766978945","https://openalex.org/W6767471572","https://openalex.org/W6769178842","https://openalex.org/W6769867024","https://openalex.org/W6781368565"],"related_works":["https://openalex.org/W3147324749","https://openalex.org/W2981087920","https://openalex.org/W2264105282","https://openalex.org/W2762594199","https://openalex.org/W2944336483","https://openalex.org/W2794517349","https://openalex.org/W2971519457","https://openalex.org/W3094122712","https://openalex.org/W2902368158","https://openalex.org/W2950354455","https://openalex.org/W2903877528","https://openalex.org/W3135357861","https://openalex.org/W3017521796","https://openalex.org/W2990163919","https://openalex.org/W2895758197","https://openalex.org/W3029678209","https://openalex.org/W2987118624","https://openalex.org/W2965034157","https://openalex.org/W3033270690"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2],"this":[3,40],"paper":[4],"is":[5,25],"text-independent":[6],"speaker":[7,23,35],"verification":[8,24],"where":[9],"utterances":[10],"come":[11],"from":[12],"'in":[13],"the":[14,34,50,54,63,68,76],"wild'":[15],"videos":[16],"and":[17],"may":[18],"contain":[19,62],"irrelevant":[20],"signal.":[21],"While":[22],"naturally":[26],"a":[27],"pair-wise":[28,69],"problem,":[29],"existing":[30],"methods":[31],"to":[32,57],"produce":[33],"embeddings":[36,60],"are":[37,73],"instance-wise.":[38],"In":[39],"paper,":[41],"we":[42],"propose":[43],"Cross":[44],"Attentive":[45],"Pooling":[46],"(CAP)":[47],"that":[48,61],"utilizes":[49],"context":[51],"information":[52,66],"across":[53],"reference-query":[55],"pair":[56],"generate":[58],"utterance-level":[59],"most":[64],"discriminative":[65],"for":[67],"matching":[70],"problem.":[71],"Experiments":[72],"performed":[74],"on":[75],"VoxCeleb":[77],"dataset":[78],"in":[79],"which":[80],"our":[81],"method":[82],"outperforms":[83],"comparable":[84],"pooling":[85],"strategies.":[86]},"counts_by_year":[{"year":2021,"cited_by_count":3}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}