{"id":"https://openalex.org/W3163139004","doi":"https://doi.org/10.1109/icassp39728.2021.9414390","title":"Content-Aware Speaker Embeddings for Speaker Diarisation","display_name":"Content-Aware Speaker Embeddings for Speaker Diarisation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163139004","doi":"https://doi.org/10.1109/icassp39728.2021.9414390","mag":"3163139004"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5077772423","display_name":"Guangzhi Sun","orcid":"https://orcid.org/0000-0002-5886-056X"},"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":"G. Sun","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077400590","display_name":"D. Liu","orcid":"https://orcid.org/0009-0008-9746-0973"},"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":"D. Liu","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007989522","display_name":"C. Zhang","orcid":"https://orcid.org/0000-0002-2173-6872"},"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":"C. Zhang","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., 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":"P. C. Woodland","raw_affiliation_strings":["Cambridge University Engineering Dept., Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept., Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077772423"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67464558,"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":"7168","last_page":"7172"},"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":0.9972000122070312,"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":0.9962999820709229,"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":0.827076256275177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7936832308769226},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7821377515792847},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7067230343818665},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6271855235099792},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5734665989875793},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5180345177650452},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.49114295840263367},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.45070549845695496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4429141581058502},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3591046929359436}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.827076256275177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7936832308769226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7821377515792847},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7067230343818665},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6271855235099792},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5734665989875793},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5180345177650452},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.49114295840263367},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.45070549845695496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4429141581058502},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3591046929359436},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":44,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W1524333225","https://openalex.org/W1710476689","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2105667909","https://openalex.org/W2114925438","https://openalex.org/W2121415728","https://openalex.org/W2132914434","https://openalex.org/W2148613904","https://openalex.org/W2210888091","https://openalex.org/W2250539671","https://openalex.org/W2288371874","https://openalex.org/W2289985966","https://openalex.org/W2401273849","https://openalex.org/W2514741789","https://openalex.org/W2597655663","https://openalex.org/W2638067502","https://openalex.org/W2748318213","https://openalex.org/W2888968865","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2936774411","https://openalex.org/W2937328535","https://openalex.org/W2938372602","https://openalex.org/W2962959915","https://openalex.org/W2963470929","https://openalex.org/W2963962398","https://openalex.org/W2972949456","https://openalex.org/W2981608174","https://openalex.org/W2983398075","https://openalex.org/W2993724474","https://openalex.org/W3015737406","https://openalex.org/W3093501662","https://openalex.org/W3134299941","https://openalex.org/W4234330420","https://openalex.org/W4298289240","https://openalex.org/W6631362777","https://openalex.org/W6637568146","https://openalex.org/W6735377749","https://openalex.org/W6769530546","https://openalex.org/W6781719301","https://openalex.org/W6784414797"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2061937230","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"Recent":[0],"speaker":[1,15,21,28,40,81,87,105,110,142],"diarisation":[2,111],"systems":[3],"often":[4],"convert":[5],"variable":[6],"length":[7],"speech":[8,52,77],"segments":[9],"into":[10],"fixed-length":[11],"vector":[12],"representations":[13],"for":[14,104],"clustering,":[16],"which":[17,34],"are":[18],"known":[19],"as":[20,69],"embeddings.":[22,59],"In":[23],"this":[24],"paper,":[25],"the":[26,36,39,92,114,120],"content-aware":[27],"embeddings":[29],"(CASE)":[30],"approach":[31],"is":[32,102,123],"proposed,":[33],"extends":[35],"input":[37],"of":[38],"classifier":[41],"to":[42,61,83,96],"include":[43],"not":[44],"only":[45],"acoustic":[46],"features":[47],"but":[48],"also":[49],"their":[50],"corresponding":[51,93],"content,":[53],"via":[54],"phone,":[55],"character,":[56],"and":[57,89],"word":[58],"Compared":[60],"alternative":[62],"methods":[63],"that":[64,136],"leverage":[65],"similar":[66],"information,":[67],"such":[68],"multitask":[70],"or":[71],"adversarial":[72],"training,":[73],"CASE":[74,101,137],"factorises":[75],"automatic":[76,131],"recognition":[78,82],"(ASR)":[79],"from":[80],"focus":[84],"on":[85,129],"modelling":[86],"characteristics":[88],"correlations":[90],"with":[91,107],"content":[94,121],"units":[95],"derive":[97],"more":[98],"expressive":[99],"representations.":[100],"evaluated":[103],"re-clustering":[106],"a":[108,139],"realistic":[109],"setup":[112],"using":[113],"AMI":[115],"meeting":[116],"transcription":[117],"dataset,":[118],"where":[119],"information":[122],"obtained":[124],"by":[125],"performing":[126],"ASR":[127],"based":[128],"an":[130],"segmentation.":[132],"Experimental":[133],"results":[134],"showed":[135],"achieved":[138],"17.8%":[140],"relative":[141],"error":[143],"rate":[144],"reduction":[145],"over":[146],"conventional":[147],"methods.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}