{"id":"https://openalex.org/W3145204487","doi":"https://doi.org/10.1109/slt48900.2021.9383617","title":"Discriminative Neural Clustering for Speaker Diarisation","display_name":"Discriminative Neural Clustering for Speaker Diarisation","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3145204487","doi":"https://doi.org/10.1109/slt48900.2021.9383617","mag":"3145204487"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5030757951","display_name":"Qiujia Li","orcid":"https://orcid.org/0000-0003-3074-3692"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Qiujia Li","raw_affiliation_strings":["Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069221660","display_name":"Florian Kreyssig","orcid":"https://orcid.org/0000-0002-8948-988X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Florian L. Kreyssig","raw_affiliation_strings":["Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip C. Woodland","raw_affiliation_strings":["Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030757951"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":3.5353,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.9378801,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"574","last_page":"581"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.86603844165802},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7320539951324463},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7016108632087708},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5882202982902527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5635384321212769},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.52619868516922},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46757960319519043},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4418407082557678},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4156709313392639},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3742375671863556},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3476887345314026},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07477834820747375}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.86603844165802},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7320539951324463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016108632087708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5882202982902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5635384321212769},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.52619868516922},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46757960319519043},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4418407082557678},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4156709313392639},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3742375671863556},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3476887345314026},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07477834820747375},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.75,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W2038101708","https://openalex.org/W2081074144","https://openalex.org/W2119717200","https://openalex.org/W2125336414","https://openalex.org/W2133564696","https://openalex.org/W2148613904","https://openalex.org/W2150458450","https://openalex.org/W2150769028","https://openalex.org/W2151834591","https://openalex.org/W2159591770","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2292479959","https://openalex.org/W2296073425","https://openalex.org/W2327501763","https://openalex.org/W2402146185","https://openalex.org/W2460742184","https://openalex.org/W2638067502","https://openalex.org/W2746574320","https://openalex.org/W2748488820","https://openalex.org/W2889060826","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2938372602","https://openalex.org/W2952992734","https://openalex.org/W2962780374","https://openalex.org/W2962788625","https://openalex.org/W2962826786","https://openalex.org/W2963403868","https://openalex.org/W2963466847","https://openalex.org/W2963470929","https://openalex.org/W2963654251","https://openalex.org/W2963745998","https://openalex.org/W2963747784","https://openalex.org/W2963962398","https://openalex.org/W2964275228","https://openalex.org/W2964308564","https://openalex.org/W2972949456","https://openalex.org/W2975711469","https://openalex.org/W2995428172","https://openalex.org/W3008357631","https://openalex.org/W3016021376","https://openalex.org/W4214556932","https://openalex.org/W4385245566","https://openalex.org/W6678809451","https://openalex.org/W6679434410","https://openalex.org/W6712930963","https://openalex.org/W6739901393","https://openalex.org/W6747544821","https://openalex.org/W6768570733","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"In":[0],"this":[1,96],"paper,":[2],"we":[3],"propose":[4],"Discriminative":[5],"Neural":[6],"Clustering":[7],"(DNC)":[8],"that":[9,135],"formulates":[10],"data":[11,37,82,100,114],"clustering":[12,29,33],"with":[13],"a":[14,20,44,62,85,90,138],"maximum":[15],"number":[16],"of":[17,43,49,122,145],"clusters":[18],"as":[19,78],"supervised":[21],"sequence-to-sequence":[22],"learning":[23],"problem.":[24],"Com-pared":[25],"to":[26,58,148],"traditional":[27],"unsupervised":[28],"algorithms,":[30],"DNC":[31,50,136],"learns":[32],"patterns":[34],"from":[35],"training":[36,89],"without":[38],"requiring":[39],"an":[40],"explicit":[41],"definition":[42],"similarity":[45],"measure.":[46],"An":[47],"implementation":[48],"based":[51],"on":[52,61,132],"the":[53,67,118],"Transformer":[54,91],"architecture":[55],"is":[56,84],"shown":[57],"be":[59],"effective":[60],"speaker":[63,128,141],"diarisation":[64],"task":[65],"using":[66],"challenging":[68],"AMI":[69,72,133],"dataset.":[70],"Since":[71],"contains":[73],"only":[74],"147":[75],"complete":[76],"meetings":[77],"individual":[79],"input":[80,105,120],"sequences,":[81],"scarcity":[83],"significant":[86],"issue":[87],"for":[88,93],"model":[92],"DNC.":[94],"Accordingly,":[95],"paper":[97],"proposes":[98],"three":[99],"augmentation":[101],"schemes:":[102],"sub-sequence":[103],"randomisation,":[104,107],"vector":[106],"and":[108],"Diaconis":[109],"augmentation,":[110],"which":[111],"generates":[112],"new":[113],"samples":[115],"by":[116],"rotating":[117],"entire":[119],"sequence":[121],"L":[123],"<sub":[124],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[125],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sub>":[126],"-normalised":[127],"embeddings.":[129],"Experimental":[130],"results":[131],"show":[134],"achieves":[137],"reduction":[139],"in":[140],"error":[142],"rate":[143],"(SER)":[144],"29.4%":[146],"relative":[147],"spectral":[149],"clustering.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}