{"id":"https://openalex.org/W4381430768","doi":"https://doi.org/10.3233/jifs-230249","title":"Speaker diarization with variants of self-attention and joint speaker embedding extractor","display_name":"Speaker diarization with variants of self-attention and joint speaker embedding extractor","publication_year":2023,"publication_date":"2023-05-30","ids":{"openalex":"https://openalex.org/W4381430768","doi":"https://doi.org/10.3233/jifs-230249"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-230249","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-230249","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","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/A5023876632","display_name":"Pengbin Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengbin Fu","raw_affiliation_strings":["Faculty of Information Technology, Beijing university of technology, Xidawang Road, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing university of technology, Xidawang Road, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100774851","display_name":"Yuchen Ma","orcid":"https://orcid.org/0000-0002-8517-8793"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Ma","raw_affiliation_strings":["Faculty of Information Technology, Beijing university of technology, Xidawang Road, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing university of technology, Xidawang Road, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037565330","display_name":"Huirong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huirong Yang","raw_affiliation_strings":["Faculty of Information Technology, Beijing university of technology, Xidawang Road, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing university of technology, Xidawang Road, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037565330"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.1751,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53299253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"45","issue":"5","first_page":"9169","last_page":"9180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8877584934234619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8124173283576965},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6531197428703308},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6023521423339844},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5574458241462708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36387598514556885},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09949034452438354}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8877584934234619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8124173283576965},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6531197428703308},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6023521423339844},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5574458241462708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36387598514556885},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09949034452438354},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-230249","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-230249","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1607302042","https://openalex.org/W2079623482","https://openalex.org/W2101775574","https://openalex.org/W2103892053","https://openalex.org/W2115426281","https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2587150483","https://openalex.org/W2597655663","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2791616807","https://openalex.org/W2890964092","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2905016804","https://openalex.org/W2939690918","https://openalex.org/W2963470929","https://openalex.org/W2963745998","https://openalex.org/W2971599855","https://openalex.org/W2972449503","https://openalex.org/W2972756562","https://openalex.org/W3007946293","https://openalex.org/W3008357631","https://openalex.org/W3015468748","https://openalex.org/W3020336359","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3081170851","https://openalex.org/W3095212884","https://openalex.org/W3119049870","https://openalex.org/W3127847680","https://openalex.org/W3138516171","https://openalex.org/W3143367551","https://openalex.org/W3178462146","https://openalex.org/W3197916665","https://openalex.org/W3212886388","https://openalex.org/W4224917363","https://openalex.org/W4283073771","https://openalex.org/W4297841547","https://openalex.org/W4307135244","https://openalex.org/W4385245566","https://openalex.org/W6670225552","https://openalex.org/W6675895153","https://openalex.org/W6688816777","https://openalex.org/W6733275487","https://openalex.org/W6735377749","https://openalex.org/W6739744869","https://openalex.org/W6739901393","https://openalex.org/W6739992741","https://openalex.org/W6754299077","https://openalex.org/W6754496211","https://openalex.org/W6764041223","https://openalex.org/W6767725219","https://openalex.org/W6776048684","https://openalex.org/W6776918098","https://openalex.org/W6777437564","https://openalex.org/W6777976503","https://openalex.org/W6782820025","https://openalex.org/W6792155083","https://openalex.org/W6792757381","https://openalex.org/W6796696476","https://openalex.org/W6810625719","https://openalex.org/W6810716790"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2148232863","https://openalex.org/W2160753975","https://openalex.org/W2161543916"],"abstract_inverted_index":{"The":[0,23,43,160],"speaker":[1,67,98,131,139],"diarization":[2,173],"task":[3],"pertains":[4],"to":[5,92,119,134],"the":[6,21,26,38,65,73,94,106,110,136,145,163,168,179,192,195],"automated":[7],"differentiation":[8],"of":[9,25,40,97,109,138,152,176,194],"speakers":[10,154],"within":[11],"an":[12],"audio":[13],"recording,":[14],"while":[15],"lacking":[16],"any":[17],"prior":[18],"information":[19,99],"regarding":[20],"speakers.":[22,42],"introduction":[24],"self-attention":[27,48,78],"mechanism":[28,49,112],"in":[29,54,61,72,100],"End-to-End":[30],"Neural":[31],"Speaker":[32],"Diarization":[33],"(EEND)":[34],"has":[35,50],"elegantly":[36],"resolved":[37],"issue":[39],"overlapping":[41],"Transformer":[44],"model":[45,91,161],"equipped":[46],"with":[47,113,162],"shown":[51],"great":[52],"potential":[53],"collecting":[55],"global":[56],"information,":[57,75],"yielding":[58],"remarkable":[59],"outcomes":[60,166],"various":[62],"tasks.":[63],"However,":[64],"individual":[66],"characteristics":[68],"are":[69],"predominantly":[70],"reflected":[71],"contextual":[74,121],"which":[76],"conventional":[77],"would":[79],"not":[80],"adequately":[81],"address.":[82],"In":[83],"this":[84],"study,":[85],"we":[86],"propose":[87],"a":[88,125,149,156,172],"hierarchical":[89],"encoders":[90],"augment":[93],"encoders\u2019":[95],"acquisition":[96],"two":[101,153],"distinct":[102],"ways:":[103],"(1)":[104],"Constraining":[105],"perceptual":[107],"field":[108],"self-attentive":[111],"left-right":[114],"windows":[115],"or":[116],"Gaussian":[117],"weights":[118],"highlight":[120],"information;":[122],"(2)":[123],"Utilizing":[124],"pre-trained":[126],"time-delay":[127],"neural":[128],"network":[129],"based":[130],"embedding":[132],"extractor":[133],"alleviate":[135],"shortcomings":[137],"feature":[140],"extraction":[141],"ability.":[142],"We":[143],"evaluate":[144],"proposed":[146,169,196],"methods":[147],"on":[148,178,184],"simulated":[150,180],"dataset":[151,181],"and":[155,182],"real":[157],"conversation":[158],"dataset.":[159],"most":[164],"favorable":[165],"among":[167],"enhancements":[170],"achieves":[171],"error":[174],"rate":[175],"7.74%":[177],"21.92%":[183],"MagicData-RAMC":[185],"after":[186],"adaptation.":[187],"These":[188],"results":[189],"compellingly":[190],"demonstrate":[191],"efficacy":[193],"methods.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}