{"id":"https://openalex.org/W4224925084","doi":"https://doi.org/10.1109/icassp43922.2022.9747301","title":"Towards end-to-end Speaker Diarization with Generalized Neural Speaker Clustering","display_name":"Towards end-to-end Speaker Diarization with Generalized Neural Speaker Clustering","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224925084","doi":"https://doi.org/10.1109/icassp43922.2022.9747301"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747301","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/A5100458065","display_name":"Chunlei Zhang","orcid":"https://orcid.org/0000-0002-6253-2446"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chunlei Zhang","raw_affiliation_strings":["Tencent AI Lab,Bellevue,USA","Tencent AI Lab, Bellevue, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Tencent AI Lab,Bellevue,USA","Tencent AI Lab, Bellevue, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770786","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0003-2554-2888"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,USA","Tencent AI Lab, Bellevue, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,USA","Tencent AI Lab, Bellevue, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100458065"],"corresponding_institution_ids":["https://openalex.org/I4210108985"],"apc_list":null,"apc_paid":null,"fwci":0.5194,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61226029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9995999932289124,"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":0.9968000054359436,"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":0.952643096446991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.780502438545227},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7283786535263062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.712489128112793},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5432331562042236},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4687132239341736},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4496878683567047},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43295055627822876},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.411540150642395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3914793133735657},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3832505941390991},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3655688166618347}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.952643096446991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.780502438545227},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7283786535263062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.712489128112793},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5432331562042236},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4687132239341736},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4496878683567047},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43295055627822876},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.411540150642395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3914793133735657},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3832505941390991},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3655688166618347},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747301","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":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1946893126","https://openalex.org/W2081074144","https://openalex.org/W2144125830","https://openalex.org/W2148613904","https://openalex.org/W2219249508","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2802973008","https://openalex.org/W2808631503","https://openalex.org/W2889031312","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2972680151","https://openalex.org/W2972949456","https://openalex.org/W3008283340","https://openalex.org/W3008357631","https://openalex.org/W3015780472","https://openalex.org/W3016031604","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3033627755","https://openalex.org/W3038871978","https://openalex.org/W3094831814","https://openalex.org/W3095212884","https://openalex.org/W3111481301","https://openalex.org/W3128434617","https://openalex.org/W3145204487","https://openalex.org/W3161158930","https://openalex.org/W3162347631","https://openalex.org/W3162899647","https://openalex.org/W3163505255","https://openalex.org/W3212886388","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6779069803","https://openalex.org/W6784351597","https://openalex.org/W6784464189","https://openalex.org/W6784806048","https://openalex.org/W6787439801","https://openalex.org/W6790122275"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W1521049138","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,34,53,149],"consists":[2],"of":[3,22,41,117,141],"many":[4],"components,":[5],"e.g.,":[6],"front-end":[7],"processing,":[8],"speech":[9,14,120],"activity":[10],"detection":[11,15],"(SAD),":[12],"overlapped":[13,119],"(OSD)":[16],"and":[17,29,38,111,121,127,157,160],"speaker":[18,33,52,59,78,129,148,158],"segmentation/clustering.":[19],"Conventionally,":[20],"most":[21],"the":[23,63,94,106,112,138,146,165],"involved":[24],"components":[25],"are":[26,36,88,134],"separately":[27],"developed":[28],"optimized.":[30],"The":[31,65,124],"resulting":[32],"systems":[35],"complicated":[37],"sometimes":[39],"lack":[40],"satisfying":[42],"generalization":[43],"capabilities.":[44],"In":[45,93],"this":[46],"study,":[47],"we":[48],"present":[49],"a":[50,56,77,83,128],"novel":[51],"system,":[54],"with":[55,90,108],"generalized":[57],"neural":[58,91],"clustering":[60,84],"module":[61,133],"as":[62],"backbone.":[64],"whole":[66],"system":[67,107,150],"can":[68],"be":[69],"simplified":[70],"to":[71,104,136,153],"contain":[72],"only":[73],"two":[74],"major":[75],"parts,":[76],"embedding":[79],"extractor":[80],"followed":[81],"by":[82],"module.":[85],"Both":[86],"parts":[87],"implemented":[89],"networks.":[92],"training":[95],"phase,":[96],"an":[97],"on-the-fly":[98],"spoken":[99],"dialogue":[100],"generator":[101],"is":[102,151],"designed":[103],"provide":[105],"audio":[109],"streams":[110],"corresponding":[113],"annotations":[114],"in":[115,164],"categories":[116],"non-speech,":[118],"active":[122],"speakers.":[123,142],"chunk-wise":[125],"inference":[126],"verification":[130],"based":[131],"tracing":[132],"conducted":[135],"handle":[137],"arbitrary":[139],"number":[140],"We":[143],"demonstrate":[144],"that":[145],"proposed":[147],"able":[152],"integrate":[154],"SAD,":[155],"OSD":[156],"segmentation/clustering,":[159],"yield":[161],"competitive":[162],"results":[163],"VoxConverse20":[166],"benchmarks.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}