{"id":"https://openalex.org/W3015678936","doi":"https://doi.org/10.1109/icassp40776.2020.9053280","title":"Context and Uncertainty Modeling for Online Speaker Change Detection","display_name":"Context and Uncertainty Modeling for Online Speaker Change Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015678936","doi":"https://doi.org/10.1109/icassp40776.2020.9053280","mag":"3015678936"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5021900623","display_name":"Hagai Aronowitz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Hagai Aronowitz","raw_affiliation_strings":["IBM Research AI,Haifa,Israel","IBM Research AI, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research AI,Haifa,Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research AI, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103551993","display_name":"Weizhong Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weizhong Zhu","raw_affiliation_strings":["IBM Research AI,Yorktown Heights,USA","IBM Research AI, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI,Yorktown Heights,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021900623"],"corresponding_institution_ids":["https://openalex.org/I4210167297"],"apc_list":null,"apc_paid":null,"fwci":0.9279,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79884035,"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":"8379","last_page":"8383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.8312394022941589},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7544458508491516},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6791329383850098},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6387687921524048},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6212685108184814},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5485202074050903},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5432350635528564},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.5313770174980164},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4878973662853241},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.46653228998184204},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43415600061416626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4324970841407776},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37030214071273804},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.36023736000061035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312394022941589},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7544458508491516},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6791329383850098},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6387687921524048},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6212685108184814},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5485202074050903},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5432350635528564},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.5313770174980164},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4878973662853241},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.46653228998184204},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43415600061416626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4324970841407776},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37030214071273804},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36023736000061035},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":33,"referenced_works":["https://openalex.org/W45771966","https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1494198834","https://openalex.org/W1597121597","https://openalex.org/W1916834241","https://openalex.org/W2010114458","https://openalex.org/W2056411660","https://openalex.org/W2064364374","https://openalex.org/W2101864798","https://openalex.org/W2121812409","https://openalex.org/W2171700247","https://openalex.org/W2405137844","https://openalex.org/W2405802804","https://openalex.org/W2408591905","https://openalex.org/W2638067502","https://openalex.org/W2673722796","https://openalex.org/W2726515241","https://openalex.org/W2746241180","https://openalex.org/W2746574320","https://openalex.org/W2748488820","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2911964094","https://openalex.org/W2936794852","https://openalex.org/W2963470929","https://openalex.org/W2963702081","https://openalex.org/W6601867588","https://openalex.org/W6628802092","https://openalex.org/W6628911050","https://openalex.org/W6640010188","https://openalex.org/W6713732491","https://openalex.org/W6714141289"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W1493012537","https://openalex.org/W2185075503","https://openalex.org/W2162158162","https://openalex.org/W2131673591","https://openalex.org/W4247736853","https://openalex.org/W2104528589","https://openalex.org/W3155728191"],"abstract_inverted_index":{"Speaker":[0],"change":[1,22,129],"detection":[2,23],"is":[3,29,82,89,100],"often":[4],"addressed":[5],"as":[6,24,50],"a":[7,25,68,143],"key":[8],"component":[9],"in":[10,84,102],"speaker":[11,21,56,64,111,117,128],"diarization":[12],"systems.":[13],"In":[14],"this":[15],"work":[16],"we":[17,42,53],"focus":[18],"on":[19,46],"online":[20,32],"standalone":[26],"task":[27],"which":[28,88,103],"required":[30],"for":[31,127],"closed":[33],"captioning":[34],"of":[35,62,77,124],"broadcast":[36],"television.":[37],"Contrary":[38],"to":[39,91,108,139],"related":[40],"works,":[41],"do":[43],"not":[44],"operate":[45],"frame-level":[47],"features":[48],"such":[49],"MFCC.":[51],"Instead,":[52],"leverage":[54],"state-of-the-art":[55],"recognition-based":[57],"technology":[58],"by":[59],"modeling":[60],"sequences":[61],"pretrained":[63],"embeddings":[65],"(x-vectors)":[66],"using":[67],"deep":[69],"neural":[70],"network.":[71],"We":[72,119],"explicitly":[73],"address":[74],"two":[75],"types":[76],"uncertainties.":[78],"The":[79,97],"first":[80],"one":[81],"uncertainty":[83,101],"embedding":[85],"point":[86],"estimate":[87],"due":[90],"short":[92],"and":[93],"varying":[94],"segment":[95],"duration.":[96],"second":[98],"type":[99],"context":[104],"segments":[105],"are":[106],"relevant":[107],"representing":[109],"the":[110,115,122],"talking":[112],"right":[113],"before":[114],"hypothesized":[116],"change.":[118],"also":[120],"show":[121],"robustness":[123],"affinity":[125],"matrix-representation":[126],"detection.":[130],"Our":[131],"methods":[132],"provide":[133],"very":[134],"significant":[135],"accuracy":[136],"improvements":[137],"compared":[138],"several":[140],"baselines":[141],"including":[142],"recently":[144],"published":[145],"end-to-end":[146],"system.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}