{"id":"https://openalex.org/W4224931294","doi":"https://doi.org/10.1109/icassp43922.2022.9746650","title":"Statistical Pyramid Dense Time Delay Neural Network for Speaker Verification","display_name":"Statistical Pyramid Dense Time Delay Neural Network for Speaker Verification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224931294","doi":"https://doi.org/10.1109/icassp43922.2022.9746650"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746650","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5004953676","display_name":"Zi-Kai Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zi-Kai Wan","raw_affiliation_strings":["Jiangsu University,School of Computer Science and Communication Engineering,China","School of Computer Science and Communication Engineering, Jiangsu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu University,School of Computer Science and Communication Engineering,China","institution_ids":["https://openalex.org/I115592961"]},{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060265416","display_name":"Qinghua Ren","orcid":"https://orcid.org/0000-0002-3441-4514"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Hua Ren","raw_affiliation_strings":["Jiangsu University,School of Computer Science and Communication Engineering,China","School of Computer Science and Communication Engineering, Jiangsu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu University,School of Computer Science and Communication Engineering,China","institution_ids":["https://openalex.org/I115592961"]},{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064159772","display_name":"You-cai Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You-Cai Qin","raw_affiliation_strings":["Jiangsu University,School of Computer Science and Communication Engineering,China","School of Computer Science and Communication Engineering, Jiangsu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu University,School of Computer Science and Communication Engineering,China","institution_ids":["https://openalex.org/I115592961"]},{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068470372","display_name":"Qirong Mao","orcid":"https://orcid.org/0000-0002-0616-4431"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi-Rong Mao","raw_affiliation_strings":["Jiangsu University,School of Computer Science and Communication Engineering,China","School of Computer Science and Communication Engineering, Jiangsu University, China","Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu University,School of Computer Science and Communication Engineering,China","institution_ids":["https://openalex.org/I115592961"]},{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, China","institution_ids":["https://openalex.org/I115592961"]},{"raw_affiliation_string":"Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6229,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66133051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7532","last_page":"7536"},"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":0.9998000264167786,"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":0.9991999864578247,"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":0.8063998222351074},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6301102638244629},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6256681680679321},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.60494464635849},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.6032559275627136},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5974065065383911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5632737874984741},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5477648377418518},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5031053423881531},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5023462772369385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063998222351074},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6301102638244629},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6256681680679321},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.60494464635849},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.6032559275627136},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5974065065383911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5632737874984741},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5477648377418518},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5031053423881531},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5023462772369385},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746650","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1899185266","https://openalex.org/W2121812409","https://openalex.org/W2560023338","https://openalex.org/W2587150483","https://openalex.org/W2612434969","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2938358845","https://openalex.org/W2940070181","https://openalex.org/W2963420686","https://openalex.org/W2964227577","https://openalex.org/W2969985801","https://openalex.org/W3010925296","https://openalex.org/W3016232124","https://openalex.org/W3024085360","https://openalex.org/W3024869864","https://openalex.org/W3095851463","https://openalex.org/W3160076723","https://openalex.org/W3197308585","https://openalex.org/W6639927594","https://openalex.org/W6737575990","https://openalex.org/W6766542914"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2022849497","https://openalex.org/W2810679507","https://openalex.org/W3081299480","https://openalex.org/W2407190427","https://openalex.org/W2907584218","https://openalex.org/W2919210741","https://openalex.org/W3002446410","https://openalex.org/W4390224712","https://openalex.org/W4322096758"],"abstract_inverted_index":{"Recently,":[0],"speaker":[1],"verification":[2],"(SV)":[3],"techniques":[4],"relay":[5],"on":[6,138,158],"deep":[7],"learning":[8,25],"frameworks":[9],"to":[10,107,129],"extract":[11],"more":[12,132],"informative":[13],"embedding":[14],"vectors,":[15],"which":[16,87,105,153],"greatly":[17],"improves":[18],"the":[19,50,59,67,82,89,93,115,126,131,139,144,155,159],"accuracy":[20],"compared":[21],"with":[22,81,162],"traditional":[23],"machine":[24],"methods.":[26],"The":[27,111],"well-known":[28],"x-vector":[29],"architecture,":[30],"a":[31],"time":[32,127],"delay":[33],"neural":[34],"network":[35],"(TDNN),":[36],"is":[37,64],"widely":[38],"adapted":[39],"for":[40],"SV":[41,160],"tasks.":[42],"However,":[43],"most":[44],"of":[45,120],"existing":[46],"variants":[47],"rarely":[48],"combines":[49],"global":[51,133],"and":[52,56,122,151],"sub-region":[53],"context":[54,90,134],"information":[55,98],"suffer":[57],"from":[58,102],"local":[60],"receptive":[61],"field":[62],"that":[63,143],"engendered":[65],"by":[66,114],"standard":[68,123],"convolutional":[69],"operation.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"propose":[75],"statistical":[76,83],"pyramid":[77,84],"dense":[78],"TDNN":[79],"(SPD-TDNN)":[80],"pooling":[85],"module":[86,95],"captures":[88],"information.":[91,135],"Specifically,":[92],"developed":[94],"adaptively":[96],"exchanges":[97],"among":[99],"contextual":[100],"regions":[101],"different":[103],"perspectives,":[104],"correspond":[106],"multiple":[108],"parallel":[109],"branches.":[110],"statistics":[112],"collected":[113],"global-region":[116],"branch":[117],"are":[118],"comprised":[119],"mean":[121],"deviation":[124],"across":[125],"domain":[128],"acquire":[130],"Extensive":[136],"experiments":[137],"VoxCeleb1&2":[140],"datasets":[141],"demonstrate":[142],"proposed":[145],"PSD-TDNN":[146],"outperforms":[147],"corresponding":[148],"D-TDNN,":[149],"D-TDNN-SS":[150],"ECAPA-TDNN":[152],"achieve":[154],"state-of-the-art":[156],"performances":[157],"task,":[161],"similar":[163],"model":[164],"complexity.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}