{"id":"https://openalex.org/W3093717751","doi":"https://doi.org/10.1109/icassp39728.2021.9414057","title":"Graph Attention Networks for Speaker Verification","display_name":"Graph Attention Networks for Speaker Verification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3093717751","doi":"https://doi.org/10.1109/icassp39728.2021.9414057","mag":"3093717751"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2010.11543","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jee-weon Jung","raw_affiliation_strings":["University of Seoul,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070613375","display_name":"Hee-Soo Heo","orcid":"https://orcid.org/0000-0003-1567-123X"},"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":"Hee-Soo Heo","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":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030475312","display_name":"Ha-Jin Yu","orcid":"https://orcid.org/0000-0003-3657-0665"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ha-Jin Yu","raw_affiliation_strings":["University of Seoul,School of Computer Science"],"affiliations":[{"raw_affiliation_string":"University of Seoul,School of Computer Science","institution_ids":["https://openalex.org/I124633538"]}]},{"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":4,"corresponding_author_ids":["https://openalex.org/A5091834525"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":0.2796,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60837116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6149","last_page":"6153"},"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/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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":0.9955999851226807,"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":0.7199087142944336},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5749956965446472},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.563004195690155},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.508056640625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45626118779182434},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4537416696548462},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43919292092323303},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4388943910598755},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.43799346685409546},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.4350692331790924},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.420502245426178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4182893931865692},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2741372585296631},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.24951082468032837},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.24394819140434265},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1873091459274292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7199087142944336},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5749956965446472},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.563004195690155},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.508056640625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45626118779182434},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4537416696548462},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43919292092323303},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4388943910598755},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.43799346685409546},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.4350692331790924},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.420502245426178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4182893931865692},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2741372585296631},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.24951082468032837},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.24394819140434265},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1873091459274292},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.11543","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11543","pdf_url":"https://arxiv.org/pdf/2010.11543","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:3093717751","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.11543.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.2010.11543","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.11543","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/j1av-1h87","is_oa":true,"landing_page_url":"https://doi.org/10.17023/j1av-1h87","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:2010.11543","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11543","pdf_url":"https://arxiv.org/pdf/2010.11543","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/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3093717751.pdf","grobid_xml":"https://content.openalex.org/works/W3093717751.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1492587309","https://openalex.org/W2049244943","https://openalex.org/W2123768812","https://openalex.org/W2150769028","https://openalex.org/W2302255633","https://openalex.org/W2404380129","https://openalex.org/W2601450892","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2779809129","https://openalex.org/W2794506738","https://openalex.org/W2802488037","https://openalex.org/W2802973008","https://openalex.org/W2808631503","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2938358845","https://openalex.org/W2962788625","https://openalex.org/W2963263347","https://openalex.org/W2963858333","https://openalex.org/W2963920355","https://openalex.org/W2964015378","https://openalex.org/W2964052309","https://openalex.org/W2964105864","https://openalex.org/W2964308564","https://openalex.org/W2972909277","https://openalex.org/W2973149080","https://openalex.org/W3004720752","https://openalex.org/W3013020904","https://openalex.org/W3016021376","https://openalex.org/W3034978746","https://openalex.org/W3035524453","https://openalex.org/W3090254849","https://openalex.org/W3104056985","https://openalex.org/W3141593045","https://openalex.org/W6629705578","https://openalex.org/W6679434410","https://openalex.org/W6726497184","https://openalex.org/W6726873649","https://openalex.org/W6726923012","https://openalex.org/W6735236233","https://openalex.org/W6745537798","https://openalex.org/W6746992151","https://openalex.org/W6774314701","https://openalex.org/W6783527727"],"related_works":["https://openalex.org/W3162463150","https://openalex.org/W2612434969","https://openalex.org/W3015412845","https://openalex.org/W3016021376","https://openalex.org/W3048784519","https://openalex.org/W2029630390","https://openalex.org/W2900022717","https://openalex.org/W3197142615","https://openalex.org/W2059222116","https://openalex.org/W3011599803","https://openalex.org/W2891049497","https://openalex.org/W3011246070","https://openalex.org/W2972892026","https://openalex.org/W2798824629","https://openalex.org/W2036420095","https://openalex.org/W2802973008","https://openalex.org/W3015596621","https://openalex.org/W3125469427","https://openalex.org/W3085067050","https://openalex.org/W2148374980"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,30,43,49,55,70,83,91,96],"novel":[4],"back-end":[5,155,170],"framework":[6,34,131],"for":[7,104,115],"speaker":[8,15,37,59,105,121,137],"verification":[9],"using":[10,57,86,134],"graph":[11,56,66,72],"attention":[12,67,73,116],"networks.":[13,68],"Segment-wise":[14],"embeddings":[16,38,60,122],"extracted":[17],"from":[18,39,123],"multiple":[19],"crops":[20],"within":[21],"an":[22,40,158],"utterance":[23,45],"are":[24],"interpreted":[25],"as":[26,111],"node":[27,79],"representations":[28],"of":[29,128,164],"graph.":[31],"The":[32,126],"proposed":[33,130],"inputs":[35],"segment-wise":[36,58,120],"enrollment":[41],"and":[42,46,61,144],"test":[44,172],"directly":[47],"outputs":[48],"similarity":[50,98,169],"score.":[51,99],"We":[52],"first":[53],"construct":[54],"then":[62],"input":[63],"these":[64],"to":[65],"After":[69],"few":[71],"layers":[74],"with":[75,141,157],"residual":[76],"connections,":[77],"each":[78],"is":[80,132],"projected":[81],"into":[82],"one-dimensional":[84],"space":[85],"affine":[87],"transform,":[88],"followed":[89],"by":[90],"readout":[92],"operation":[93],"resulting":[94],"in":[95],"scalar":[97],"To":[100],"enable":[101],"successful":[102],"adaptation":[103],"verification,":[106],"we":[107],"propose":[108],"techniques":[109],"such":[110],"separating":[112],"trainable":[113],"weights":[114],"map":[117],"calculations":[118],"between":[119],"different":[124,136,142],"utterances.":[125],"effectiveness":[127],"the":[129,167],"validated":[133],"three":[135],"embedding":[138],"extractors":[139],"trained":[140],"architectures":[143],"objective":[145],"functions.":[146],"Experimental":[147],"results":[148],"demonstrate":[149],"consistent":[150],"improvement":[151,163],"over":[152,166],"various":[153],"baseline":[154],"classifiers,":[156],"average":[159],"equal":[160],"error":[161],"rate":[162],"20%":[165],"cosine":[168],"without":[171],"time":[173],"augmentation.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}