{"id":"https://openalex.org/W4313590886","doi":"https://doi.org/10.1109/taslp.2022.3231709","title":"Memory Storable Network Based Feature Aggregation for Speaker Representation Learning","display_name":"Memory Storable Network Based Feature Aggregation for Speaker Representation Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4313590886","doi":"https://doi.org/10.1109/taslp.2022.3231709"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3231709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3231709","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101875578","display_name":"Bin Gu","orcid":"https://orcid.org/0000-0003-1621-7311"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Gu","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100436848","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1124-0854"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101875578"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.226,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82292975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"31","issue":null,"first_page":"643","last_page":"655"},"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":0.9984999895095825,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9926999807357788,"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/discriminative-model","display_name":"Discriminative model","score":0.8019313216209412},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7287737727165222},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.7121557593345642},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6796525120735168},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6201640963554382},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6195303797721863},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5754600763320923},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.544298529624939},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5439507961273193},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5316720008850098},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.531478226184845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46946799755096436},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.45610836148262024},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.428982675075531},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1433182954788208},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07633328437805176}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8019313216209412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287737727165222},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.7121557593345642},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6796525120735168},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6201640963554382},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6195303797721863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5754600763320923},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.544298529624939},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5439507961273193},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5316720008850098},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.531478226184845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46946799755096436},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.45610836148262024},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.428982675075531},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1433182954788208},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07633328437805176},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3231709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3231709","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G634576251","display_name":null,"funder_award_id":"62101523","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6450856609","display_name":null,"funder_award_id":"U1836219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W1993482042","https://openalex.org/W2046056978","https://openalex.org/W2107638917","https://openalex.org/W2109761419","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2404617565","https://openalex.org/W2516631658","https://openalex.org/W2549139847","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2740832349","https://openalex.org/W2748665871","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2889016587","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2935898178","https://openalex.org/W2938358845","https://openalex.org/W2962959915","https://openalex.org/W2963418523","https://openalex.org/W2963420686","https://openalex.org/W2963446838","https://openalex.org/W2969985801","https://openalex.org/W2972441390","https://openalex.org/W2972552635","https://openalex.org/W2972627751","https://openalex.org/W2972633940","https://openalex.org/W2972712416","https://openalex.org/W2978904488","https://openalex.org/W2979593053","https://openalex.org/W3015261361","https://openalex.org/W3015412845","https://openalex.org/W3020953549","https://openalex.org/W3024869864","https://openalex.org/W3049278490","https://openalex.org/W3095992690","https://openalex.org/W3096529494","https://openalex.org/W3103152812","https://openalex.org/W3134744625","https://openalex.org/W3142516134","https://openalex.org/W3163059624","https://openalex.org/W3174649707","https://openalex.org/W3197111314","https://openalex.org/W3205878676","https://openalex.org/W4214503194","https://openalex.org/W4221165746","https://openalex.org/W4224214057","https://openalex.org/W4224924624","https://openalex.org/W4226230385","https://openalex.org/W4289752563","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6702877178","https://openalex.org/W6729983426","https://openalex.org/W6766380642","https://openalex.org/W6800175519","https://openalex.org/W6803094557","https://openalex.org/W6810176035"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W3119773509","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611"],"abstract_inverted_index":{"Learning":[0],"fixed-dimensional":[1],"speaker":[2,13,133],"representation":[3],"using":[4,158],"deep":[5],"neural":[6],"networks":[7],"is":[8,155],"a":[9,28,51,59,162],"key":[10],"step":[11],"in":[12,166],"verification.":[14],"In":[15],"this":[16],"work,":[17],"we":[18],"propose":[19],"an":[20],"auxiliary":[21],"memory":[22],"storable":[23],"network":[24,30],"(MSN)":[25],"to":[26,41,54,129],"assist":[27],"backbone":[29,85,96,126,170],"for":[31],"learning":[32],"discriminative":[33,132],"features,":[34],"which":[35],"are":[36,97,127],"sequentially":[37],"aggregated":[38],"from":[39,75,82,117],"lower":[40],"deeper":[42],"layers":[43,120],"of":[44,61,90,104,121,151],"the":[45,55,72,76,80,83,95,101,105,115,118,125,152],"backbone.":[46],"The":[47,87,149],"proposed":[48,153],"MSN":[49,123],"has":[50],"similar":[52],"architecture":[53],"ResNet":[56],"and":[57,79,111,124,143],"contains":[58],"set":[60],"cascaded":[62],"feature":[63],"aggregation":[64],"(FA)":[65],"blocks.":[66],"Each":[67],"FA":[68,107],"block":[69,78,108],"first":[70],"aggregates":[71],"multi-level":[73,102],"features":[74,81,89,103,116],"previous":[77],"corresponding":[84,106],"layer.":[86],"output":[88],"each":[91],"intermediate":[92],"layer":[93],"within":[94],"then":[98],"refined":[99],"by":[100],"through":[109],"masking":[110],"biasing":[112],"operations.":[113],"Finally,":[114],"last":[119],"both":[122],"concatenated":[128],"form":[130],"more":[131],"representations.":[134],"Experimental":[135],"results":[136],"on":[137],"five":[138],"public":[139],"datasets":[140],"show":[141],"significant":[142],"consistent":[144],"improvements":[145],"over":[146],"conventional":[147],"approaches.":[148],"effectiveness":[150],"method":[154],"also":[156],"validated":[157],"ablation":[159],"studies,":[160],"showing":[161],"robust":[163],"generalization":[164],"capacity":[165],"combination":[167],"with":[168],"different":[169],"networks.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}