{"id":"https://openalex.org/W4372268583","doi":"https://doi.org/10.1109/icassp49357.2023.10095530","title":"Advancing the Dimensionality Reduction of Speaker Embeddings for Speaker Diarisation: Disentangling Noise and Informing Speech Activity","display_name":"Advancing the Dimensionality Reduction of Speaker Embeddings for Speaker Diarisation: Disentangling Noise and Informing Speech Activity","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372268583","doi":"https://doi.org/10.1109/icassp49357.2023.10095530"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095530","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":"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/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":true,"raw_author_name":"You Jin Kim","raw_affiliation_strings":["Naver Cloud Corporation,South Korea","Naver Cloud Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Cloud Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Cloud 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 Cloud Corporation,South Korea","Naver Cloud Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Cloud Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Cloud 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 Cloud Corporation,South Korea","Naver Cloud Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Cloud Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Cloud Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","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":false,"raw_author_name":"Youngki Kwon","raw_affiliation_strings":["Naver Cloud Corporation,South Korea","Naver Cloud Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Cloud Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Cloud 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 Cloud Corporation,South Korea","Naver Cloud Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Cloud Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Cloud 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/A5022133103"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63060284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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":0.747624933719635},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.73508620262146},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6605009436607361},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6355744004249573},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6318634152412415},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.599651575088501},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5900307893753052},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4971502125263214},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4760541617870331},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4420163929462433},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4319293200969696},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4185488224029541},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.41219183802604675},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4103385806083679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38303422927856445},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20118576288223267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10880392789840698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.747624933719635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.73508620262146},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6605009436607361},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6355744004249573},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6318634152412415},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.599651575088501},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5900307893753052},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4971502125263214},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4760541617870331},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4420163929462433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4319293200969696},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4185488224029541},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.41219183802604675},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4103385806083679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38303422927856445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20118576288223267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10880392789840698},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095530","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":0.5099999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2889418727","https://openalex.org/W2939131199","https://openalex.org/W2963460857","https://openalex.org/W2963470929","https://openalex.org/W2972449503","https://openalex.org/W2981103786","https://openalex.org/W3002433751","https://openalex.org/W3010196324","https://openalex.org/W3015544392","https://openalex.org/W3016031604","https://openalex.org/W3025075133","https://openalex.org/W3038871978","https://openalex.org/W3095212884","https://openalex.org/W3095410713","https://openalex.org/W3100378519","https://openalex.org/W3111481301","https://openalex.org/W3146417844","https://openalex.org/W3196595845","https://openalex.org/W3196857193","https://openalex.org/W3197331597","https://openalex.org/W3197762688","https://openalex.org/W4214556932","https://openalex.org/W4289490880","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6754215057","https://openalex.org/W6768584815","https://openalex.org/W6769656443","https://openalex.org/W6774558098","https://openalex.org/W6786127183","https://openalex.org/W6787439801","https://openalex.org/W6802591457"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W3141593045","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"The":[0],"objective":[1],"of":[2,24,103,120],"this":[3,75],"work":[4,41],"is":[5],"to":[6,49,68,71,81,107],"train":[7],"noise-robust":[8],"speaker":[9,13,98,110],"embeddings":[10,16],"adapted":[11],"for":[12],"diarisation.":[14],"Speaker":[15],"play":[17],"a":[18,86,118],"crucial":[19],"role":[20],"in":[21],"the":[22,52,97,101,109,114,130],"performance":[23,132],"diarisation":[25],"systems,":[26],"but":[27],"they":[28,56],"often":[29],"capture":[30],"spurious":[31,94],"information":[32,62,95],"such":[33,61],"as":[34],"noise,":[35],"adversely":[36],"affecting":[37],"performance.":[38],"Our":[39],"previous":[40],"has":[42],"proposed":[43],"an":[44],"auto-encoder-based":[45],"dimensionality":[46,88],"reduction":[47,89],"module":[48],"help":[50],"remove":[51],"redundant":[53],"information.":[54],"However,":[55],"do":[57],"not":[58],"explicitly":[59],"separate":[60],"and":[63],"have":[64],"also":[65],"been":[66],"found":[67],"be":[69],"sensitive":[70],"hyper-parameter":[72],"values.":[73],"To":[74],"end,":[76],"we":[77],"propose":[78],"two":[79],"contributions":[80],"overcome":[82],"these":[83],"issues:":[84],"(i)":[85],"novel":[87],"framework":[90],"that":[91],"can":[92],"disentangle":[93],"from":[96,112],"embeddings;":[99],"(ii)":[100],"use":[102],"speech":[104],"activity":[105],"vector":[106],"prevent":[108],"code":[111],"representing":[113],"background":[115],"noise.":[116],"Through":[117],"range":[119],"experiments":[121],"conducted":[122],"on":[123],"four":[124],"datasets,":[125],"our":[126],"approach":[127],"consistently":[128],"demonstrates":[129],"state-of-the-art":[131],"among":[133],"models":[134],"without":[135],"system":[136],"fusion.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
