{"id":"https://openalex.org/W2794506738","doi":"https://doi.org/10.21437/interspeech.2018-993","title":"Attentive Statistics Pooling for Deep Speaker Embedding","display_name":"Attentive Statistics Pooling for Deep Speaker Embedding","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2794506738","doi":"https://doi.org/10.21437/interspeech.2018-993","mag":"2794506738"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-993","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-993","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.10963","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031351840","display_name":"Koji Okabe","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Koji Okabe","raw_affiliation_strings":["Data Science Research Laboratories, NEC Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Data Science Research Laboratories, NEC Corporation, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031109112","display_name":"Takafumi Koshinaka","orcid":"https://orcid.org/0000-0002-2343-5125"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Koshinaka","raw_affiliation_strings":["Data Science Research Laboratories, NEC Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Data Science Research Laboratories, NEC Corporation, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Shinoda","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031351840"],"corresponding_institution_ids":["https://openalex.org/I118347220"],"apc_list":null,"apc_paid":null,"fwci":36.8482,"has_fulltext":false,"cited_by_count":496,"citation_normalized_percentile":{"value":0.99753204,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2252","last_page":"2256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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":0.8484655618667603},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.8009016513824463},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7301899194717407},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7132689952850342},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6768113970756531},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6298868656158447},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6205630302429199},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5382866859436035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5167586207389832},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4713708162307739},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44289910793304443},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4198342561721802},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.38723334670066833},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08078309893608093}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8484655618667603},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8009016513824463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301899194717407},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7132689952850342},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6768113970756531},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6298868656158447},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6205630302429199},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5382866859436035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167586207389832},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4713708162307739},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44289910793304443},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4198342561721802},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.38723334670066833},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08078309893608093},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2018-993","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-993","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:arXiv.org:1803.10963","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.10963","pdf_url":"https://arxiv.org/pdf/1803.10963","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":null,"raw_type":"text"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50422716","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100771284","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"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":{"id":"pmh:oai:arXiv.org:1803.10963","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.10963","pdf_url":"https://arxiv.org/pdf/1803.10963","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1528954144","https://openalex.org/W1589137271","https://openalex.org/W2039057510","https://openalex.org/W2114925438","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2201092681","https://openalex.org/W2242685705","https://openalex.org/W2395102671","https://openalex.org/W2395750323","https://openalex.org/W2515626571","https://openalex.org/W2612434969","https://openalex.org/W2726515241","https://openalex.org/W2746742816","https://openalex.org/W2748488820","https://openalex.org/W2890964092","https://openalex.org/W2917756095","https://openalex.org/W2962959915","https://openalex.org/W4234330420"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W66821593","https://openalex.org/W2051274299","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W2767892728","https://openalex.org/W468945283","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W215245425"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"attentive":[3],"statistics":[4],"pooling":[5],"for":[6],"deep":[7],"speaker":[8,12,16,68],"embedding":[9],"in":[10,67],"text-independent":[11],"verification.":[13],"In":[14,59],"conventional":[15,94],"embedding,":[17],"frame-level":[18],"features":[19],"are":[20],"averaged":[21],"over":[22],"all":[23],"the":[24,75,80,93],"frames":[25,47],"of":[26],"a":[27],"single":[28],"utterance":[29],"to":[30,41,45],"form":[31],"an":[32,38],"utterance-level":[33],"feature.":[34],"Our":[35],"method":[36,95],"utilizes":[37],"attention":[39],"mechanism":[40],"give":[42],"different":[43,46],"weights":[44],"and":[48,79,98],"generates":[49],"not":[50],"only":[51],"weighted":[52,56],"means":[53],"but":[54],"also":[55],"standard":[57],"deviations.":[58],"this":[60],"way,":[61],"it":[62,86],"can":[63],"capture":[64],"long-term":[65],"variations":[66],"characteristics":[69],"more":[70],"effectively.":[71],"An":[72],"evaluation":[73],"on":[74],"NIST":[76],"SRE":[77],"2012":[78],"VoxCeleb":[81],"data":[82],"sets":[83],"shows":[84],"that":[85],"reduces":[87],"equal":[88],"error":[89],"rates":[90],"(EERs)":[91],"from":[92],"by":[96],"7.5%":[97],"8.1%,":[99],"respectively.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":45},{"year":2024,"cited_by_count":67},{"year":2023,"cited_by_count":75},{"year":2022,"cited_by_count":87},{"year":2021,"cited_by_count":90},{"year":2020,"cited_by_count":78},{"year":2019,"cited_by_count":46},{"year":2018,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}