{"id":"https://openalex.org/W4408353456","doi":"https://doi.org/10.1109/icassp49660.2025.10888681","title":"Multi-channel Speaker Counting for EEND-VC-based Speaker Diarization on Multi-domain Conversation","display_name":"Multi-channel Speaker Counting for EEND-VC-based Speaker Diarization on Multi-domain Conversation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353456","doi":"https://doi.org/10.1109/icassp49660.2025.10888681"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5073111123","display_name":"Naohiro Tawara","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naohiro Tawara","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103279502","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0003-1586-0356"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":3.346,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90339339,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"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":0.9715999960899353,"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":0.9715999960899353,"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":0.9362999796867371,"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":0.8350329995155334},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7806971073150635},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598773241043091},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6445410847663879},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5033976435661316},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46810388565063477},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46166402101516724},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16899362206459045},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12507906556129456},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.12006998062133789},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06135338544845581}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8350329995155334},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7806971073150635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598773241043091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6445410847663879},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5033976435661316},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46810388565063477},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46166402101516724},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16899362206459045},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12507906556129456},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.12006998062133789},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06135338544845581},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":28,"referenced_works":["https://openalex.org/W1969299255","https://openalex.org/W1983812858","https://openalex.org/W2164502538","https://openalex.org/W2171784699","https://openalex.org/W2563666542","https://openalex.org/W2889418727","https://openalex.org/W2900212944","https://openalex.org/W2972949456","https://openalex.org/W2997419692","https://openalex.org/W3020336359","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3097263872","https://openalex.org/W3140898556","https://openalex.org/W3163903701","https://openalex.org/W3196781856","https://openalex.org/W3196857193","https://openalex.org/W3209984917","https://openalex.org/W4220731890","https://openalex.org/W4389315122","https://openalex.org/W4389315128","https://openalex.org/W4389315129","https://openalex.org/W4389315131","https://openalex.org/W4392904174","https://openalex.org/W4402111631","https://openalex.org/W4403640427","https://openalex.org/W4403640476","https://openalex.org/W7033105191"],"related_works":["https://openalex.org/W2206035908","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/W4406496871","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,15],"speaker":[4,19,32,39,100,105,121,144],"counting":[5,40,122,145],"scheme":[6,134],"using":[7,71],"multichannel":[8,60],"microphones":[9,114],"for":[10],"end-to-end":[11],"neural":[12],"diarization":[13,20,140],"with":[14,45,91,152],"vector":[16],"clustering":[17,31],"(EEND-VC)":[18],"pipeline.":[21],"The":[22,132],"EEND-VC-based":[23],"system":[24],"estimates":[25],"the":[26,55,64,76,88,104,149,158],"number":[27,65],"of":[28,66],"speakers":[29],"by":[30,53,79],"embeddings":[33,58,72],"from":[34,59,108],"small":[35],"chunks.":[36],"However,":[37],"conventional":[38],"struggles":[41],"in":[42,70,157],"short":[43,109],"sessions":[44],"limited":[46],"available":[47],"embeddings.":[48,67],"We":[49],"address":[50],"this":[51,84],"issue":[52],"leveraging":[54],"most":[56],"possible":[57],"signals":[61],"to":[62,102,119,148],"increase":[63],"One":[68],"challenge":[69],"across":[73],"channels":[74],"is":[75],"biases":[77],"caused":[78],"channel":[80],"differences.":[81],"To":[82],"mitigate":[83],"issue,":[85],"we":[86],"extend":[87],"EEND-VC":[89],"pipeline":[90],"two":[92],"modifications:":[93],"(1)":[94],"applying":[95],"speech":[96],"enhancement":[97],"before":[98],"extracting":[99],"embedding":[101],"capture":[103],"characteristics":[106],"even":[107],"chunks":[110],"and":[111,126,154,160],"(2)":[112],"grouping":[113],"based":[115],"on":[116],"inter-channel":[117],"correlation":[118],"perform":[120],"within":[123],"each":[124],"group":[125],"then":[127],"aggregating":[128],"these":[129],"channel-wise":[130],"results.":[131],"proposed":[133],"was":[135],"integrated":[136],"into":[137],"our":[138],"CHiME-8":[139,150],"pipeline,":[141],"achieving":[142],"superior":[143],"accuracy":[146],"compared":[147],"baseline,":[151],"54.2%":[153],"61.4%":[155],"improvements":[156],"development":[159],"evaluation":[161],"sets,":[162],"respectively.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}