{"id":"https://openalex.org/W3204593031","doi":"https://doi.org/10.1109/icassp43922.2022.9747450","title":"Multi-Scale Speaker Embedding-Based Graph Attention Networks For Speaker Diarisation","display_name":"Multi-Scale Speaker Embedding-Based Graph Attention Networks For Speaker Diarisation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3204593031","doi":"https://doi.org/10.1109/icassp43922.2022.9747450","mag":"3204593031"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747450","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5067505925","display_name":"Youngki Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Youngki Kwon","raw_affiliation_strings":["Naver Corporation,South Korea","Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070613375","display_name":"Hee-Soo Heo","orcid":"https://orcid.org/0000-0003-1567-123X"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hee-Soo Heo","raw_affiliation_strings":["Naver Corporation,South Korea","Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jee-Weon Jung","raw_affiliation_strings":["Naver Corporation,South Korea","Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022133103","display_name":"You Jin Kim","orcid":"https://orcid.org/0000-0002-4952-5532"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"You Jin Kim","raw_affiliation_strings":["Naver Corporation,South Korea","Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086369397","display_name":"Bong\u2010Jin Lee","orcid":"https://orcid.org/0000-0001-7896-2961"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bong-Jin Lee","raw_affiliation_strings":["Naver Corporation,South Korea","Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5067505925"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":1.4552,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.83441069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8367","last_page":"8371"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8393612504005432},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7579562664031982},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.690093457698822},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5596188902854919},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5554415583610535},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.505406379699707},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5045298337936401},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.493943989276886},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4852449893951416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4813055098056793},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4628976881504059},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.376503586769104},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2610096335411072}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8393612504005432},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7579562664031982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.690093457698822},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5596188902854919},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5554415583610535},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.505406379699707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5045298337936401},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.493943989276886},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4852449893951416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4813055098056793},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4628976881504059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.376503586769104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2610096335411072},{"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/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/icassp43922.2022.9747450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747450","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1591607137","https://openalex.org/W2125336414","https://openalex.org/W2132914434","https://openalex.org/W2518108298","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2765407302","https://openalex.org/W2808631503","https://openalex.org/W2889418727","https://openalex.org/W2963263347","https://openalex.org/W2963399829","https://openalex.org/W2963403868","https://openalex.org/W2963858333","https://openalex.org/W2964121744","https://openalex.org/W2972449503","https://openalex.org/W2972949456","https://openalex.org/W2981103786","https://openalex.org/W3008357631","https://openalex.org/W3038871978","https://openalex.org/W3095212884","https://openalex.org/W3108962419","https://openalex.org/W3135990229","https://openalex.org/W3162347631","https://openalex.org/W3162463150","https://openalex.org/W3162687954","https://openalex.org/W3163505255","https://openalex.org/W3196595845","https://openalex.org/W3197014136","https://openalex.org/W3197331597","https://openalex.org/W3198455895","https://openalex.org/W3198827946","https://openalex.org/W3200167423","https://openalex.org/W3201773091","https://openalex.org/W3208240190","https://openalex.org/W4214556932","https://openalex.org/W4297733535","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6678809451","https://openalex.org/W6726497184","https://openalex.org/W6739901393","https://openalex.org/W6745136726","https://openalex.org/W6745537798","https://openalex.org/W6763509872","https://openalex.org/W6768584815","https://openalex.org/W6786127183","https://openalex.org/W6791480293","https://openalex.org/W6800885585","https://openalex.org/W6801088966","https://openalex.org/W6802591457"],"related_works":["https://openalex.org/W4384929466","https://openalex.org/W2206035908","https://openalex.org/W3148366653","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138"],"abstract_inverted_index":{"The":[0],"objective":[1],"of":[2,30,51,83,122,143],"this":[3,43,93,101],"work":[4],"is":[5,15],"effective":[6],"speaker":[7,11,24,111,151],"diarisation":[8],"using":[9,66],"multi-scale":[10,52,110,138],"embeddings.":[12],"Typically,":[13],"there":[14],"a":[16,67,89,133],"trade-off":[17],"between":[18],"the":[19,27,31,35,49,62,72,77,81,128,141,150,155,166],"ability":[20],"to":[21,34,118,131,165],"recognise":[22],"short":[23],"segments":[25,55],"and":[26],"discriminative":[28],"power":[29],"embedding,":[32],"according":[33],"segment":[36,84],"length":[37],"used":[38],"for":[39,109],"embedding":[40],"extraction.":[41],"To":[42],"end,":[44],"recent":[45],"works":[46],"have":[47],"proposed":[48],"use":[50],"embeddings":[53],"where":[54,71,149],"with":[56],"varying":[57],"lengths":[58,85],"are":[59,64,74],"used.":[60],"However,":[61],"scores":[63],"combined":[65],"weighted":[68],"summation":[69],"scheme":[70],"weights":[73],"fixed":[75],"after":[76],"training":[78],"phase,":[79],"whereas":[80],"importance":[82],"can":[86],"differ":[87],"within":[88],"single":[90],"session.To":[91],"address":[92],"issue,":[94],"we":[95,104,114,126],"present":[96],"three":[97],"key":[98],"contributions":[99],"in":[100,146,161],"paper:":[102],"(1)":[103],"propose":[105],"graph":[106],"attention":[107],"networks":[108],"diarisation;":[112],"(2)":[113],"design":[115],"scale":[116,120],"indicators":[117],"utilise":[119,132],"information":[121],"each":[123],"embedding;":[124],"(3)":[125],"adapt":[127],"attention-based":[129],"aggregation":[130],"pre-computed":[134],"affinity":[135],"matrix":[136],"from":[137],"embeddings.We":[139],"demonstrate":[140],"effectiveness":[142],"our":[144],"method":[145],"various":[147],"datasets":[148],"confusion":[152],"which":[153],"constitutes":[154],"primary":[156],"metric":[157],"drops":[158],"over":[159],"10%":[160],"average":[162],"relative":[163],"compared":[164],"baseline.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}