{"id":"https://openalex.org/W4362683557","doi":"https://doi.org/10.1109/taslp.2023.3265199","title":"ANSD-MA-MSE: Adaptive Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding","display_name":"ANSD-MA-MSE: Adaptive Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4362683557","doi":"https://doi.org/10.1109/taslp.2023.3265199"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3265199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3265199","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/A5018657729","display_name":"Maokui He","orcid":null},"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":"Mao-Kui He","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3772-0939","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"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":"Jun Du","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349220","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0001-8857-6677"},"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":"Qing-Feng Liu","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1892-2551","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9656,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.94525136,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"1561","last_page":"1573"},"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":0.9988999962806702,"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":0.9983000159263611,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.839923083782196},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7511324286460876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6705517768859863},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6502155065536499},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6227179169654846},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5564948916435242},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4471578001976013},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4146888852119446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35774940252304077},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3298163414001465}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.839923083782196},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7511324286460876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6705517768859863},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6502155065536499},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6227179169654846},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5564948916435242},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4471578001976013},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4146888852119446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35774940252304077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3298163414001465},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3265199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3265199","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":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1713836045","display_name":null,"funder_award_id":"62171427","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1482605500","https://openalex.org/W1494198834","https://openalex.org/W1589339348","https://openalex.org/W1607302042","https://openalex.org/W1890834058","https://openalex.org/W1965819578","https://openalex.org/W2010114458","https://openalex.org/W2038101708","https://openalex.org/W2067191022","https://openalex.org/W2081074144","https://openalex.org/W2093499222","https://openalex.org/W2098726438","https://openalex.org/W2101775574","https://openalex.org/W2107638917","https://openalex.org/W2117678320","https://openalex.org/W2121812409","https://openalex.org/W2127218421","https://openalex.org/W2142940228","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2293634267","https://openalex.org/W2638067502","https://openalex.org/W2889041236","https://openalex.org/W2889381673","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2915347754","https://openalex.org/W2946638775","https://openalex.org/W2963470929","https://openalex.org/W2972680151","https://openalex.org/W2972869740","https://openalex.org/W2972949456","https://openalex.org/W2988502885","https://openalex.org/W3007946293","https://openalex.org/W3008357631","https://openalex.org/W3015544392","https://openalex.org/W3016031604","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3095212884","https://openalex.org/W3097643313","https://openalex.org/W3111481301","https://openalex.org/W3126581785","https://openalex.org/W3128688470","https://openalex.org/W3135990229","https://openalex.org/W3178462146","https://openalex.org/W3195050710","https://openalex.org/W3196595845","https://openalex.org/W3197980326","https://openalex.org/W3208240190","https://openalex.org/W3212886388","https://openalex.org/W4224917363","https://openalex.org/W4288091954","https://openalex.org/W6623517193","https://openalex.org/W6628911050","https://openalex.org/W6633847657","https://openalex.org/W6678914141","https://openalex.org/W6754192381","https://openalex.org/W6769178842","https://openalex.org/W6787439801","https://openalex.org/W6790297703","https://openalex.org/W6790412463","https://openalex.org/W6791480293","https://openalex.org/W6802591457","https://openalex.org/W6840066292","https://openalex.org/W6931392099"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,18,28,36,50,94,131],"neural":[6,106],"speaker":[7,32,42,51,70,107],"diarization":[8,108,117,161],"(NSD)":[9],"network":[10],"architecture":[11],"consisting":[12],"of":[13,31,63,137],"three":[14],"key":[15],"components.":[16],"First,":[17],"memory-aware":[19,110],"multi-speaker":[20,111],"embedding":[21,33,43,112],"(MA-MSE)":[22],"mechanism":[23],"is":[24,54,65,80,179],"proposed":[25,81,103,153],"to":[26,34,56,82],"facilitate":[27],"dynamical":[29],"refinement":[30],"reduce":[35],"potential":[37],"data":[38],"mismatch":[39],"between":[40],"the":[41,46,60,68,73,84,89,144,148,165,169,174],"extraction":[44],"and":[45,130,147],"NSD":[47,74],"network.":[48,75],"Next,":[49],"selection":[52],"procedure":[53,79],"introduced":[55],"handle":[57],"situations":[58],"where":[59],"detected":[61],"number":[62,136],"speakers":[64],"different":[66],"from":[67],"assumed":[69],"size":[71],"in":[72,93,119,160,173],"Finally,":[76],"an":[77],"adaptive":[78,105],"improve":[83],"required":[85],"prior":[86],"information":[87],"for":[88],"nonoverlap":[90],"speech":[91],"segments":[92],"given":[95],"utterance":[96],"during":[97],"each":[98],"iteration.":[99],"We":[100],"call":[101],"our":[102,152],"framework":[104],"with":[109],"(ANSD-MA-MSE).":[113],"Our":[114,177],"method":[115],"improves":[116],"performance":[118],"realistic":[120],"operating":[121],"scenarios,":[122],"such":[123],"as":[124],"adverse":[125],"acoustic":[126],"environments,":[127],"domain":[128],"mismatches,":[129],"varying,":[132],"rather":[133],"than":[134],"fixed,":[135],"speakers.":[138],"Having":[139],"been":[140],"tested":[141],"on":[142],"both":[143],"AMI":[145],"corpus":[146],"DIHARD-III":[149,175],"evaluation":[150],"sets,":[151],"approach":[154],"consistently":[155],"outperforms":[156],"other":[157],"state-of-the-art":[158],"techniques":[159],"error":[162],"rates,":[163],"including":[164],"results":[166],"reported":[167],"by":[168],"best":[170],"single-model":[171],"system":[172],"challenge.":[176],"code":[178],"publicly":[180],"available":[181],"at":[182],"<uri":[183],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[184],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Maokui-He/NSD-MA-MSE</uri>":[185],".":[186]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}