{"id":"https://openalex.org/W3015253990","doi":"https://doi.org/10.1109/icassp40776.2020.9054350","title":"Statistics Pooling Time Delay Neural Network Based on X-Vector for Speaker Verification","display_name":"Statistics Pooling Time Delay Neural Network Based on X-Vector for Speaker Verification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015253990","doi":"https://doi.org/10.1109/icassp40776.2020.9054350","mag":"3015253990"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5054849851","display_name":"Qian-Bei Hong","orcid":"https://orcid.org/0000-0003-2123-1601"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]},{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Qian-Bei Hong","raw_affiliation_strings":["Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University and Academia Sinica, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University and Academia Sinica, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558","https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103251327","display_name":"Chung\u2010Hsien Wu","orcid":"https://orcid.org/0000-0002-3947-2123"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]},{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Hsien Wu","raw_affiliation_strings":["Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University and Academia Sinica, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University and Academia Sinica, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558","https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]},{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University and Academia Sinica, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University and Academia Sinica, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558","https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103086620","display_name":"Chien-Lin Huang","orcid":"https://orcid.org/0000-0003-3157-4173"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chien-Lin Huang","raw_affiliation_strings":["PingAn AI Lab, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PingAn AI Lab, Palo Alto, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4895,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86123831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6849","last_page":"6853"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9984999895095825,"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":0.8001664280891418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7651404142379761},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6399859189987183},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6052960753440857},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5831862092018127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5595149993896484},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.48643970489501953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48183906078338623},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4488983154296875},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43733346462249756},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.42086225748062134},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4104040861129761}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8001664280891418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651404142379761},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6399859189987183},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6052960753440857},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5831862092018127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5595149993896484},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.48643970489501953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48183906078338623},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4488983154296875},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43733346462249756},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.42086225748062134},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4104040861129761},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2114925438","https://openalex.org/W2117671523","https://openalex.org/W2123768812","https://openalex.org/W2290689761","https://openalex.org/W2516764878","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2770454110","https://openalex.org/W2808631503","https://openalex.org/W2888897023","https://openalex.org/W2889492015","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2916301830","https://openalex.org/W2938358845","https://openalex.org/W2963470929"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W4317103504","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"to":[3,40],"improve":[4],"speaker":[5,17,77,120],"embedding":[6],"representation":[7],"based":[8],"on":[9,64,94,123],"x-vector":[10,62],"for":[11,16,37,76],"extracting":[12],"more":[13],"detailed":[14],"information":[15],"verification.":[18,78],"We":[19],"propose":[20],"a":[21],"statistics":[22,35],"pooling":[23,36],"time":[24],"delay":[25],"neural":[26],"network":[27],"(TDNN),":[28],"in":[29,47,71,104],"which":[30],"the":[31,42,60,65,69,72,84,91,99,105,110,115,119,124],"TDNN":[32],"structure":[33],"integrates":[34],"each":[38],"layer,":[39],"consider":[41],"variation":[43],"of":[44],"temporal":[45],"context":[46],"frame-level":[48],"transformation.":[49],"The":[50,79],"proposed":[51,85,111],"feature":[52],"vector,":[53],"named":[54],"as":[55],"statsvector,":[56],"are":[57],"compared":[58],"with":[59,87],"baseline":[61],"features":[63],"VoxCeleb":[66],"dataset":[67,75],"and":[68,117],"Speakers":[70],"Wild":[73],"(SITW)":[74],"experimental":[80],"results":[81],"showed":[82],"that":[83,109],"stats-vector":[86],"score":[88],"fusion":[89],"achieved":[90],"best":[92],"performance":[93,122],"VoxCeleb1":[95],"dataset.":[96,126],"Furthermore,":[97],"considering":[98],"interference":[100,116],"from":[101],"other":[102],"speakers":[103],"recordings,":[106],"we":[107],"found":[108],"statsvector":[112],"efficiently":[113],"reduced":[114],"improved":[118],"verification":[121],"SITW":[125]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}