{"id":"https://openalex.org/W4319862441","doi":"https://doi.org/10.1109/slt54892.2023.10023184","title":"Joint Speaker Diarisation and Tracking in Switching State-Space Model","display_name":"Joint Speaker Diarisation and Tracking in Switching State-Space Model","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862441","doi":"https://doi.org/10.1109/slt54892.2023.10023184"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023184","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023184","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5048201022","display_name":"Jeremy H. M. Wong","orcid":"https://orcid.org/0000-0003-3742-7510"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Jeremy H. M. Wong","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR,Singapore","Institute for Infocomm Research, A*STAR, Singapore","Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR,Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft,USA","Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0059747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"146","issue":null,"first_page":"605","last_page":"612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991000294685364,"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":0.7625486850738525},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.6502031087875366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5957840085029602},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5679272413253784},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.560912549495697},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5548181533813477},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5532327890396118},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5124316811561584},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.48781970143318176},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48368388414382935},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4482094943523407},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4444385766983032},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.43089205026626587},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4289237856864929},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.386238157749176},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.3252827525138855},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2289026975631714},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16423863172531128},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1297980546951294},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12585937976837158},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11501076817512512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7625486850738525},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.6502031087875366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5957840085029602},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5679272413253784},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.560912549495697},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5548181533813477},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5532327890396118},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5124316811561584},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.48781970143318176},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48368388414382935},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4482094943523407},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4444385766983032},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.43089205026626587},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4289237856864929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.386238157749176},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.3252827525138855},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2289026975631714},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16423863172531128},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1297980546951294},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12585937976837158},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11501076817512512},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023184","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023184","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":49,"referenced_works":["https://openalex.org/W1484181928","https://openalex.org/W1504771832","https://openalex.org/W1989471337","https://openalex.org/W1993815147","https://openalex.org/W2024668293","https://openalex.org/W2033166104","https://openalex.org/W2052545911","https://openalex.org/W2071949631","https://openalex.org/W2082542916","https://openalex.org/W2098613108","https://openalex.org/W2101206777","https://openalex.org/W2102716594","https://openalex.org/W2105862065","https://openalex.org/W2113386290","https://openalex.org/W2126736494","https://openalex.org/W2131958840","https://openalex.org/W2156255174","https://openalex.org/W2166263464","https://openalex.org/W2170951662","https://openalex.org/W2222512263","https://openalex.org/W2289985966","https://openalex.org/W2332774781","https://openalex.org/W2538804860","https://openalex.org/W2563666542","https://openalex.org/W2903510073","https://openalex.org/W2972680151","https://openalex.org/W2997419692","https://openalex.org/W3008283340","https://openalex.org/W3008819336","https://openalex.org/W3015544392","https://openalex.org/W3021261768","https://openalex.org/W3102937397","https://openalex.org/W3105031100","https://openalex.org/W3142516134","https://openalex.org/W3160741541","https://openalex.org/W4214556932","https://openalex.org/W4220731890","https://openalex.org/W4224916247","https://openalex.org/W4225661121","https://openalex.org/W4251232855","https://openalex.org/W6628802092","https://openalex.org/W6630130805","https://openalex.org/W6647494281","https://openalex.org/W6675410064","https://openalex.org/W6730678351","https://openalex.org/W6756739727","https://openalex.org/W6771611251","https://openalex.org/W6774453931","https://openalex.org/W6798513510"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1879255185","https://openalex.org/W1977167953","https://openalex.org/W2162158162","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W4247736853","https://openalex.org/W1980506188","https://openalex.org/W1493012537","https://openalex.org/W1999004162"],"abstract_inverted_index":{"Speakers":[0],"may":[1],"move":[2],"around":[3],"while":[4,72],"diarisation":[5,43,75,128],"is":[6,13,83,106,130],"being":[7],"performed.":[8],"When":[9],"a":[10,56,77,109,114],"microphone":[11],"array":[12],"used,":[14],"the":[15,20,42,68,86,90,93,98,122],"instantaneous":[16],"locations":[17,100],"of":[18,70,92,101],"where":[19,85],"sounds":[21],"originated":[22],"from":[23],"can":[24,35],"be":[25,36],"estimated,":[26],"and":[27,97,127],"previous":[28],"investigations":[29],"have":[30],"shown":[31],"that":[32,50,121,138],"such":[33],"information":[34],"complementary":[37],"to":[38,65,132],"speaker":[39,96],"embeddings":[40],"in":[41],"task.":[44],"However,":[45],"these":[46],"approaches":[47],"often":[48],"assume":[49],"speakers":[51,71],"are":[52],"fairly":[53],"stationary":[54],"throughout":[55],"meeting.":[57],"This":[58],"paper":[59],"relaxes":[60],"this":[61],"assumption,":[62],"by":[63],"proposing":[64],"explicitly":[66],"track":[67],"movements":[69],"jointly":[73],"performing":[74],"within":[76],"unified":[78],"model.":[79],"A":[80],"state-space":[81],"model":[82,105],"proposed,":[84],"hidden":[87],"state":[88],"expresses":[89],"identity":[91],"current":[94],"active":[95],"predicted":[99],"all":[102],"speakers.":[103],"The":[104],"implemented":[107],"as":[108],"particle":[110],"filter.":[111],"Experiments":[112],"on":[113],"Microsoft":[115],"rich":[116],"meeting":[117],"transcription":[118],"task":[119],"show":[120],"proposed":[123],"joint":[124],"location":[125,140],"tracking":[126],"approach":[129],"able":[131],"perform":[133],"comparably":[134],"with":[135],"other":[136],"methods":[137],"use":[139],"information.":[141]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}