{"id":"https://openalex.org/W2889519245","doi":"https://doi.org/10.21437/interspeech.2018-1158","title":"Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification","display_name":"Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889519245","doi":"https://doi.org/10.21437/interspeech.2018-1158","mag":"2889519245"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1158","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5064702198","display_name":"Yingke Zhu","orcid":"https://orcid.org/0000-0002-9370-6082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingke Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059065394","display_name":"David Snyder","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Snyder","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059141717","display_name":"Brian Mak","orcid":"https://orcid.org/0000-0001-6787-5555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Mak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":255,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3573","last_page":"3577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"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":0.9954000115394592,"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":0.9854000210762024,"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":0.7809262275695801},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7489629983901978},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7125797867774963},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6204383373260498},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5918890833854675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4847685694694519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3723418414592743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809262275695801},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7489629983901978},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7125797867774963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6204383373260498},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5918890833854675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4847685694694519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3723418414592743}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2018-1158","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-94402","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-94402","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-94402","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=2308-457X&rft.volume=v. 2018-September&rft.issue=&rft.date=2018&rft.spage=3573&rft.aulast=Zhu&rft.aufirst=Y.&rft.atitle=Self-attentive+speaker+embeddings+for+text-independent+speaker+verification&rft.title=Proceedings+of+the+Annual+Conference+of+the+International+Speech+Communication+Association%2C+INTERSPEECH","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2253551762","https://openalex.org/W1521049138","https://openalex.org/W1516392727","https://openalex.org/W2140022733","https://openalex.org/W3048612421","https://openalex.org/W2911612049","https://openalex.org/W2160753975","https://openalex.org/W2150532155","https://openalex.org/W3012250009","https://openalex.org/W2378903289"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,11,26,38,64,68,80,97,102,121],"new":[4],"method":[5],"to":[6,50,92,107],"extract":[7],"speaker":[8,18,21,61,115,146],"embeddings":[9,22,135,147],"from":[10,25,44],"deep":[12],"neural":[13],"network":[14],"(DNN)":[15],"for":[16],"text-independent":[17],"verification.":[19],"Usually,":[20],"are":[23,48,76,89],"extracted":[24],"speaker-classification":[27],"DNN":[28,123],"that":[29,132],"averages":[30],"the":[31,35,40,46,60,133,140,144],"hidden":[32,41,71],"vectors":[33,42],"over":[34],"frames":[36,47],"of":[37,67,85,96,110],"speaker;":[39],"produced":[43,142],"all":[45],"assumed":[49],"be":[51],"equally":[52],"important.":[53],"We":[54,130],"relax":[55],"this":[56],"assumption":[57],"and":[58,73,153],"compute":[59],"embedding":[62,116,124],"as":[63],"weighted":[65],"average":[66],"speaker's":[69,98],"frame-level":[70],"vectors,":[72],"their":[74],"weights":[75],"automatically":[77],"determined":[78],"by":[79,143],"self-attention":[81],"mechanism.":[82],"The":[83,112],"effect":[84],"multiple":[86],"attention":[87],"heads":[88],"also":[90],"investigated":[91],"capture":[93],"different":[94],"aspects":[95],"input":[99],"speech.":[100],"Finally,":[101],"PLDA":[103],"classifier":[104],"is":[105,118,148],"used":[106],"compare":[108],"pairs":[109],"embeddings.":[111],"proposed":[113],"self-attentive":[114,134,145],"system":[117],"compared":[119],"with":[120,150],"strong":[122],"baseline":[125],"on":[126],"NIST":[127],"SRE":[128],"2016.":[129],"find":[131],"achieve":[136],"superior":[137],"performance.":[138],"Moreover,":[139],"improvement":[141],"consistent":[149],"both":[151],"short":[152],"long":[154],"testing":[155],"utterances.":[156],"\u00a9":[157],"2018":[158],"International":[159],"Speech":[160],"Communication":[161],"Association.":[162],"All":[163],"rights":[164],"reserved.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":42},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":71},{"year":2019,"cited_by_count":38},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}