{"id":"https://openalex.org/W3135006803","doi":"https://doi.org/10.1109/iscslp49672.2021.9362097","title":"Revisiting the Statistics Pooling Layer in Deep Speaker Embedding Learning","display_name":"Revisiting the Statistics Pooling Layer in Deep Speaker Embedding Learning","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3135006803","doi":"https://doi.org/10.1109/iscslp49672.2021.9362097","mag":"3135006803"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100328272","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-1595-3619"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering, AI Institute, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057050425","display_name":"Yexin Yang","orcid":"https://orcid.org/0000-0001-9597-9829"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yexin Yang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering, AI Institute, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering, AI Institute, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering, AI Institute, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering, AI Institute, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9962000250816345,"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":0.9943000078201294,"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":0.9222120642662048},{"id":"https://openalex.org/keywords/standard-deviation","display_name":"Standard deviation","score":0.7791380882263184},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5575016140937805},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5487410426139832},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5129660964012146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4993135929107666},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4855734705924988},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38059258460998535},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35817742347717285}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9222120642662048},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.7791380882263184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5575016140937805},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5487410426139832},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5129660964012146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4993135929107666},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4855734705924988},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38059258460998535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35817742347717285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W204053250","https://openalex.org/W1006777433","https://openalex.org/W1524333225","https://openalex.org/W1677182931","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2150769028","https://openalex.org/W2404617565","https://openalex.org/W2587150483","https://openalex.org/W2601789736","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2889519245","https://openalex.org/W2890704021","https://openalex.org/W2890964092","https://openalex.org/W2900156001","https://openalex.org/W2916104401","https://openalex.org/W2919115771","https://openalex.org/W2926256696","https://openalex.org/W2936614765","https://openalex.org/W2936733796","https://openalex.org/W2956925952","https://openalex.org/W2962761264","https://openalex.org/W2962832278","https://openalex.org/W2963077989","https://openalex.org/W2963450999","https://openalex.org/W2963759317","https://openalex.org/W2981087920","https://openalex.org/W2981461916","https://openalex.org/W4288091954","https://openalex.org/W6608353291","https://openalex.org/W6631362777","https://openalex.org/W6740167877","https://openalex.org/W6760797648","https://openalex.org/W6761549388","https://openalex.org/W6769178842"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W3182189390"],"abstract_inverted_index":{"The":[0],"pooling":[1,33,38,91,121],"function":[2],"plays":[3],"a":[4,53,73],"vital":[5],"role":[6],"in":[7,57,68],"the":[8,21,24,28,61,79,86,113,117,130,136,141],"segment-level":[9],"deep":[10],"speaker":[11],"embedding":[12],"learning":[13],"framework.":[14],"One":[15],"common":[16],"method":[17],"is":[18],"to":[19,77],"calculate":[20],"statistics":[22,37,83,119],"of":[23,75,81],"temporal":[25,31,36],"features,":[26],"while":[27],"mean":[29,42],"based":[30,93,120],"average":[32],"(TAP)":[34],"and":[35,43,88,98,110,112,128],"(TSTP)":[39],"which":[40],"combine":[41],"standard":[44,62,95,132],"deviation":[45,133],"are":[46,105],"two":[47],"typical":[48],"approaches.":[49],"Empirically,":[50],"researchers":[51],"observe":[52],"big":[54],"performance":[55,125,138],"degradation":[56],"x-vector":[58],"when":[59],"removing":[60],"deviation.":[63],"Based":[64],"on":[65,90,94,108,139],"this":[66,69],"observation,":[67],"paper,":[70],"we":[71],"designed":[72],"set":[74],"experiments":[76],"analyze":[78],"effectiveness":[80],"different":[82],"quantitatively,":[84],"including":[85],"investigation":[87],"comparison":[89],"functions":[92,122],"deviation,":[96],"covariance":[97],"\u2113":[99],"<sub":[100],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[101],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">p</sub>":[102],"-norm.":[103],"Experiments":[104],"carried":[106],"out":[107],"Vox-Celeb":[109],"SRE16,":[111],"results":[114],"show":[115],"that":[116],"second-order":[118],"yield":[123],"better":[124],"than":[126],"TAP,":[127],"only":[129],"simple":[131],"can":[134],"achieve":[135],"best":[137],"all":[140],"evaluation":[142],"conditions.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}