{"id":"https://openalex.org/W2963962398","doi":"https://doi.org/10.1109/icassp.2019.8683373","title":"Speaker Diarisation Using 2D Self-attentive Combination of Embeddings","display_name":"Speaker Diarisation Using 2D Self-attentive Combination of Embeddings","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2963962398","doi":"https://doi.org/10.1109/icassp.2019.8683373","mag":"2963962398"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":true,"raw_author_name":"G. Sun","raw_affiliation_strings":["Cambridge University Engineering Dept, Trumpington St, Cambridge, CB2 1PZ, U.K","Cambridge University Engineering Dept, Trumpington St, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept, Trumpington St, Cambridge, CB2 1PZ, U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]},{"raw_affiliation_string":"Cambridge University Engineering Dept, Trumpington St, Cambridge, U.K","institution_ids":["https://openalex.org/I4210096386","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"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"C. Zhang","raw_affiliation_strings":["Cambridge University Engineering Dept, Trumpington St, Cambridge, CB2 1PZ, U.K","Cambridge University Engineering Dept, Trumpington St, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept, Trumpington St, Cambridge, CB2 1PZ, U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]},{"raw_affiliation_string":"Cambridge University Engineering Dept, Trumpington St, Cambridge, U.K","institution_ids":["https://openalex.org/I4210096386","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"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"P. C. Woodland","raw_affiliation_strings":["Cambridge University Engineering Dept, Trumpington St, Cambridge, CB2 1PZ, U.K","Cambridge University Engineering Dept, Trumpington St, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Dept, Trumpington St, Cambridge, CB2 1PZ, U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]},{"raw_affiliation_string":"Cambridge University Engineering Dept, Trumpington St, Cambridge, U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077772423"],"corresponding_institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"],"apc_list":null,"apc_paid":null,"fwci":3.3604,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93979896,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5801","last_page":"5805"},"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":0.9990000128746033,"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":0.9987999796867371,"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":0.6746370792388916},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6678798198699951},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5040684938430786},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.48234695196151733},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4579121470451355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4464690089225769},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42867106199264526},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3442494571208954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34008848667144775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6746370792388916},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6678798198699951},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5040684938430786},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.48234695196151733},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4579121470451355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4464690089225769},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42867106199264526},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3442494571208954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34008848667144775},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W142991516","https://openalex.org/W1606894530","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2046056978","https://openalex.org/W2098726438","https://openalex.org/W2114925438","https://openalex.org/W2125336414","https://openalex.org/W2148613904","https://openalex.org/W2150769028","https://openalex.org/W2402146185","https://openalex.org/W2405970501","https://openalex.org/W2518112949","https://openalex.org/W2576165910","https://openalex.org/W2584329820","https://openalex.org/W2597655663","https://openalex.org/W2638067502","https://openalex.org/W2743167696","https://openalex.org/W2888968865","https://openalex.org/W2889176060","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2962832278","https://openalex.org/W2962959915","https://openalex.org/W2963470929","https://openalex.org/W6678809451","https://openalex.org/W6712930963","https://openalex.org/W6713679436","https://openalex.org/W6732884072","https://openalex.org/W6735377749","https://openalex.org/W6742972455","https://openalex.org/W6745983287"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W42295635","https://openalex.org/W1973996291","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W2330575325","https://openalex.org/W4388890789"],"abstract_inverted_index":{"Speaker":[0],"diarisation":[1],"systems":[2],"often":[3,21],"cluster":[4],"audio":[5],"segments":[6],"using":[7,174],"speaker":[8,153],"embeddings":[9,19],"such":[10],"as":[11,41],"i-vectors":[12],"and":[13,84,90,159,164],"d-vectors.":[14],"Since":[15],"different":[16,67,124],"types":[17,68,72],"of":[18,69,73,114],"are":[20,81],"complementary,":[22],"this":[23,79],"paper":[24,80],"proposes":[25],"a":[26,36,42,47,165],"generic":[27],"framework":[28],"to":[29,40,111,120],"improve":[30],"performance":[31],"by":[32,58,157],"combining":[33],"them":[34],"into":[35],"single":[37,89],"embedding,":[38],"referred":[39],"c-vector.":[43],"This":[44],"combination":[45,83],"uses":[46],"2-dimensional":[48],"(2D)":[49],"self-attentive":[50,56,75,92,101,181],"structure,":[51],"which":[52,87,103],"extends":[53],"the":[54,99,108,129,133,139,150,175],"standard":[55],"layer":[57],"averaging":[59],"not":[60,122],"only":[61,123],"across":[62,66],"time":[63],"but":[64,127],"also":[65,118,128],"embeddings.":[70],"Two":[71],"2D":[74,180],"structure":[76],"studied":[77],"in":[78,98,132],"simultaneous":[82],"consecutive":[85],"combination,":[86],"adopt":[88],"multiple":[91,134],"layers":[93],"respectively.":[94],"The":[95],"penalty":[96,147],"term":[97,148],"original":[100],"layer,":[102],"is":[104,117],"jointly":[105],"minimised":[106],"with":[107],"objective":[109],"function":[110],"encourage":[112],"diversity":[113],"annotation":[115,135],"vectors,":[116],"modified":[119,146],"obtain":[121],"local":[125],"peaks":[126],"overall":[130],"trends":[131],"vectors.":[136],"Experiments":[137],"on":[138],"AMI":[140],"meeting":[141],"corpus":[142],"show":[143],"that":[144],"our":[145,178],"improves":[149],"d-vector":[151,162],"relative":[152,168],"error":[154],"rate":[155],"(SER)":[156],"6%":[158],"21%":[160],"for":[161],"systems,":[163],"10%":[166],"further":[167],"SER":[169],"reduction":[170],"can":[171],"be":[172],"obtained":[173],"c-vector":[176],"from":[177],"best":[179],"structure.":[182]},"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":10},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
