{"id":"https://openalex.org/W4392969512","doi":"https://doi.org/10.1109/icassp48485.2024.10446724","title":"Joint Inference of Speaker Diarization and ASR with Multi-Stage Information Sharing","display_name":"Joint Inference of Speaker Diarization and ASR with Multi-Stage Information Sharing","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392969512","doi":"https://doi.org/10.1109/icassp48485.2024.10446724"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100372965","display_name":"Weiqing Wang","orcid":"https://orcid.org/0000-0002-9578-819X"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weiqing Wang","raw_affiliation_strings":["Duke University,Department of Electrical & Computer Engineering,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical & Computer Engineering,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090055875","display_name":"Danwei Cai","orcid":"https://orcid.org/0000-0002-5122-0623"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danwei Cai","raw_affiliation_strings":["Duke University,Department of Electrical & Computer Engineering,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical & Computer Engineering,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101639327","display_name":"Ming Cheng","orcid":"https://orcid.org/0000-0003-1819-650X"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Cheng","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Duke University,Department of Electrical & Computer Engineering,Durham,NC,USA,27708","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical & Computer Engineering,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100372965"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":0.6632,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72221382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11011","last_page":"11015"},"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":0.9986000061035156,"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":0.9980000257492065,"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":0.961743950843811},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7806856632232666},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6820476055145264},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6225922107696533},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6128143668174744},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5516605377197266},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44317489862442017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38148170709609985},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34203585982322693},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06977680325508118}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.961743950843811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806856632232666},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6820476055145264},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6225922107696533},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6128143668174744},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5516605377197266},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44317489862442017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38148170709609985},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34203585982322693},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06977680325508118},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W996208672","https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2794506738","https://openalex.org/W2963227667","https://openalex.org/W2963745998","https://openalex.org/W2972743990","https://openalex.org/W2972949456","https://openalex.org/W2974231335","https://openalex.org/W2981103786","https://openalex.org/W2999547272","https://openalex.org/W3004750774","https://openalex.org/W3008357631","https://openalex.org/W3024400986","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3095822285","https://openalex.org/W3128688470","https://openalex.org/W3135990229","https://openalex.org/W3160133086","https://openalex.org/W3178462146","https://openalex.org/W3196595845","https://openalex.org/W3203417382","https://openalex.org/W4224917363","https://openalex.org/W4234330420","https://openalex.org/W4362683557","https://openalex.org/W4375868885","https://openalex.org/W4375868932","https://openalex.org/W4400033122","https://openalex.org/W6633097512","https://openalex.org/W6688816777","https://openalex.org/W6767671539","https://openalex.org/W6768584815","https://openalex.org/W6790297703","https://openalex.org/W6791480293"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","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":[0,53],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"a":[5,18,39,82,132],"novel":[6],"approach":[7,80],"that":[8,78],"unifies":[9],"Automatic":[10],"Speech":[11],"Recognition":[12],"(ASR)":[13],"and":[14,141,151],"speaker":[15,130,152],"diarization":[16,51,63,102],"in":[17],"cohesive":[19],"framework.":[20],"Utilizing":[21],"the":[22,25,35,46,55,62,73,101,107],"synergies":[23],"between":[24],"two":[26],"tasks,":[27],"our":[28,79,110,120],"method":[29],"effectively":[30],"extracts":[31],"speaker-specific":[32],"information":[33],"from":[34],"lower":[36],"layers":[37,48],"of":[38,57,87,109],"pretrained":[40],"Conformer-based":[41],"ASR":[42,58,98,139,150],"model":[43],"while":[44],"leveraging":[45],"higher":[47],"for":[49,128],"enhanced":[50],"performance.":[52],"particular,":[54],"integration":[56],"contextual":[59],"details":[60],"into":[61,100],"process":[64],"has":[65],"been":[66],"demonstrated":[67],"to":[68,94,123],"be":[69,91],"effective.":[70],"Results":[71],"on":[72],"DIHARD":[74],"III":[75],"dataset":[76],"indicate":[77],"achieves":[81],"Diarization":[83],"Error":[84],"Rate":[85],"(DER)":[86],"10.52%,":[88],"which":[89,135],"can":[90,136],"further":[92,137],"reduced":[93],"10.39%":[95],"when":[96],"integrating":[97],"features":[99],"model.":[103],"These":[104],"findings":[105],"highlight":[106],"potential":[108],"approach,":[111],"suggesting":[112],"competitive":[113],"performance":[114],"against":[115],"other":[116],"state-of-the-art":[117],"systems.":[118],"Additionally,":[119],"framework\u2019s":[121],"ability":[122],"simultaneously":[124],"generate":[125],"text":[126],"transcripts":[127],"each":[129],"marks":[131],"distinct":[133],"advantage,":[134],"enhance":[138],"capabilities":[140],"transition":[142],"towards":[143],"an":[144],"end-to-end":[145],"multitask":[146],"framework":[147],"encompassing":[148],"both":[149],"diarization.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}