{"id":"https://openalex.org/W4375869365","doi":"https://doi.org/10.1109/icassp49357.2023.10096993","title":"Spectral Clustering-Aware Learning of Embeddings for Speaker Diarisation","display_name":"Spectral Clustering-Aware Learning of Embeddings for Speaker Diarisation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869365","doi":"https://doi.org/10.1109/icassp49357.2023.10096993"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5065999451","display_name":"Evonne P. C. Lee","orcid":null},"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":"Evonne P.C. Lee","raw_affiliation_strings":["Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007755497","display_name":"Guangzhi Sun","orcid":"https://orcid.org/0000-0003-3190-497X"},"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":"Guangzhi Sun","raw_affiliation_strings":["Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460139","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-1018-4144"},"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,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ","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,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9980000257492065,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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":0.7109137177467346},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.6933667063713074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6426810622215271},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.601742148399353},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.6000462174415588},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5859322547912598},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.517716646194458},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5103299021720886},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5055296421051025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.501223087310791},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4995131492614746},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48136430978775024},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4118275046348572},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.41025179624557495},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09368777275085449}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7109137177467346},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.6933667063713074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6426810622215271},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.601742148399353},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.6000462174415588},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5859322547912598},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.517716646194458},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5103299021720886},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5055296421051025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.501223087310791},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4995131492614746},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48136430978775024},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4118275046348572},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.41025179624557495},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09368777275085449},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321848","display_name":"Cambridge Trust","ror":"https://ror.org/05sprqy15"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2096733369","https://openalex.org/W2114925438","https://openalex.org/W2125336414","https://openalex.org/W2132914434","https://openalex.org/W2148613904","https://openalex.org/W2601450892","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2888968865","https://openalex.org/W2962788625","https://openalex.org/W2963466847","https://openalex.org/W2963470929","https://openalex.org/W2973049979","https://openalex.org/W2997419692","https://openalex.org/W3008357631","https://openalex.org/W3013020904","https://openalex.org/W3036601975","https://openalex.org/W3093501662","https://openalex.org/W3105031100","https://openalex.org/W3145204487","https://openalex.org/W3160397447","https://openalex.org/W3160743249","https://openalex.org/W3178462146","https://openalex.org/W3197580070","https://openalex.org/W3198275944","https://openalex.org/W3198506310","https://openalex.org/W3202370288","https://openalex.org/W3203417382","https://openalex.org/W3206189675","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W4214556932","https://openalex.org/W4285044984","https://openalex.org/W6678809451","https://openalex.org/W6735236233","https://openalex.org/W6754564145","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2412815366","https://openalex.org/W2181956362","https://openalex.org/W2136153680","https://openalex.org/W2972577568"],"abstract_inverted_index":{"In":[0,22],"speaker":[1,3,19,65,94,103,130],"diarisation,":[2],"embedding":[4],"extraction":[5],"models":[6],"often":[7],"suffer":[8],"from":[9,64],"the":[10,18,27,38,57,60,68,89,128],"mismatch":[11],"between":[12,59],"their":[13],"training":[14],"loss":[15,53],"functions":[16],"and":[17,67,75,110],"clustering":[20,84],"method.":[21],"this":[23],"paper,":[24],"we":[25],"propose":[26],"method":[28],"of":[29,33],"spectral":[30,83],"clustering-aware":[31],"learning":[32],"embeddings":[34,66,95],"(SCALE)":[35],"to":[36,123],"address":[37],"mismatch.":[39],"Specifically,":[40],"besides":[41],"an":[42],"angular":[43],"prototypical":[44],"(AP)":[45],"loss,":[46],"SCALE":[47,70,98],"uses":[48],"a":[49,124],"novel":[50],"affinity":[51,61],"matrix":[52,62],"which":[54],"directly":[55],"minimises":[56],"error":[58,104,115],"estimated":[63],"reference.":[69],"also":[71],"includes":[72],"p-percentile":[73],"thresholding":[74],"Gaussian":[76],"blur":[77],"as":[78],"two":[79],"important":[80],"hyper-parameters":[81],"for":[82],"in":[85],"training.":[86],"Experiments":[87],"on":[88],"AMI":[90],"dataset":[91],"showed":[92],"that":[93],"obtained":[96],"with":[97,127],"achieved":[99],"over":[100,111],"50%":[101],"relative":[102,113],"rate":[105,116],"reductions":[106,117],"using":[107,118],"oracle":[108],"segmentation,":[109],"30%":[112],"diarisation":[114],"automatic":[119],"segmentation":[120],"when":[121],"compared":[122],"strong":[125],"baseline":[126],"AP-loss-based":[129],"embeddings.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}