{"id":"https://openalex.org/W4221165661","doi":"https://doi.org/10.1109/icassp43922.2022.9746234","title":"Tight Integration Of Neural- And Clustering-Based Diarization Through Deep Unfolding Of Infinite Gaussian Mixture Model","display_name":"Tight Integration Of Neural- And Clustering-Based Diarization Through Deep Unfolding Of Infinite Gaussian Mixture Model","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221165661","doi":"https://doi.org/10.1109/icassp43922.2022.9746234"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746234","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":"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/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034538103","display_name":"Tomoharu Iwata","orcid":"https://orcid.org/0000-0003-4425-1971"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoharu Iwata","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8382","last_page":"8386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987000226974487,"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":0.9983000159263611,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8066906929016113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7376177906990051},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7205100059509277},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5993949174880981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5179244875907898},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4767645001411438},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4540354907512665},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45370784401893616},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45156314969062805},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.41638222336769104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3813851773738861},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3419751226902008},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3206222653388977}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8066906929016113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376177906990051},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7205100059509277},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5993949174880981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5179244875907898},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4767645001411438},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4540354907512665},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45370784401893616},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45156314969062805},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.41638222336769104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3813851773738861},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3419751226902008},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206222653388977},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746234","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2032916024","https://openalex.org/W2072169887","https://openalex.org/W2081074144","https://openalex.org/W2109176692","https://openalex.org/W2125336414","https://openalex.org/W2151967501","https://openalex.org/W2162833336","https://openalex.org/W2219249508","https://openalex.org/W2587150483","https://openalex.org/W2696967604","https://openalex.org/W2734774145","https://openalex.org/W2889381673","https://openalex.org/W2889418727","https://openalex.org/W2891054259","https://openalex.org/W2896538040","https://openalex.org/W2917756095","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3095212884","https://openalex.org/W3128434617","https://openalex.org/W3135048627","https://openalex.org/W3163903701","https://openalex.org/W3196857193","https://openalex.org/W3200796884","https://openalex.org/W3208240190","https://openalex.org/W4225661121","https://openalex.org/W4235169531","https://openalex.org/W4244030505","https://openalex.org/W4297801963","https://openalex.org/W6638670064","https://openalex.org/W6682569104","https://openalex.org/W6684050148","https://openalex.org/W6688816777","https://openalex.org/W6779253965","https://openalex.org/W6791432711"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1197719229","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W106647055","https://openalex.org/W1992796048"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,25,158],"has":[2],"been":[3],"investigated":[4],"extensively":[5],"as":[6],"an":[7,39],"important":[8],"central":[9],"task":[10],"for":[11,75],"meeting":[12],"analysis.":[13],"Recent":[14],"trend":[15],"shows":[16],"that":[17,122,147,169],"integration":[18,62,98],"of":[19,43,157,174],"end-to-end":[20],"neural":[21],"(EEND)-":[22],"and":[23,45],"clustering-based":[24],"is":[26],"a":[27,92,102,130],"promising":[28],"approach":[29,150,154],"to":[30],"handle":[31],"realistic":[32],"conversational":[33],"data":[34,145],"containing":[35],"overlapped":[36],"speech":[37],"with":[38],"arbitrarily":[40],"large":[41],"number":[42],"speakers,":[44],"achieved":[46],"state-of-the-art":[47],"results":[48,141],"on":[49,129,135,143],"various":[50],"tasks.":[51],"However,":[52],"the":[53,65,77,82,97,107,114,148,152,172,175],"approaches":[54],"proposed":[55,149,176],"so":[56],"far":[57],"have":[58],"not":[59,70],"realized":[60],"tight":[61],"yet,":[63],"because":[64],"clustering":[66,76,94,132],"employed":[67],"therein":[68],"was":[69],"optimal":[71],"in":[72,155],"any":[73],"sense":[74],"speaker":[78,115,166],"embeddings":[79,116],"estimated":[80],"by":[81,100,163],"EEND":[83],"module.":[84],"To":[85],"address":[86],"this":[87,89],"problem,":[88],"paper":[90],"introduces":[91],"trainable":[93],"algorithm":[95],"into":[96],"framework,":[99],"deep-unfolding":[101],"non-parametric":[103],"Bayesian":[104],"model":[105,111],"called":[106],"infinite":[108],"Gaussian":[109],"mixture":[110],"(iGMM).":[112],"Specifically,":[113],"are":[117],"optimized":[118],"during":[119],"training":[120],"such":[121],"it":[123],"better":[124],"fits":[125],"iGMM":[126,177],"clustering,":[127],"based":[128,134,142],"novel":[131],"loss":[133],"Adjusted":[136],"Rand":[137],"Index":[138],"(ARI).":[139],"Experimental":[140],"CALLHOME":[144],"show":[146],"outperforms":[151],"conventional":[153],"terms":[156],"error":[159],"rate":[160],"(DER),":[161],"especially":[162],"substantially":[164],"reducing":[165],"confusion":[167],"errors,":[168],"indeed":[170],"reflects":[171],"effectiveness":[173],"integration.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}