{"id":"https://openalex.org/W4406495809","doi":"https://doi.org/10.1109/slt61566.2024.10832160","title":"Investigation of Speaker Representation for Target-Speaker Speech Processing","display_name":"Investigation of Speaker Representation for Target-Speaker Speech Processing","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406495809","doi":"https://doi.org/10.1109/slt61566.2024.10832160"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"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":"Takanori Ashihara","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/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"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":"Takafumi Moriya","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":"middle","author":{"id":"https://openalex.org/A5111291634","display_name":"Junyi Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Junyi Peng","raw_affiliation_strings":["Brno University of Technology,Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"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":"Tsubasa Ochiai","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/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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014468963","display_name":"Kohei Matsuura","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":"Kohei Matsuura","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/A5049917170","display_name":"Hiroshi Sat\u014d","orcid":"https://orcid.org/0000-0002-5899-1340"},"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":"Hiroshi Sato","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":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"423","last_page":"430"},"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":0.9995999932289124,"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":0.9976999759674072,"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-recognition","display_name":"Speaker recognition","score":0.7840622663497925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7706134915351868},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7380083799362183},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6010503172874451},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5348362922668457},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4894760847091675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32595181465148926}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7840622663497925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706134915351868},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7380083799362183},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6010503172874451},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5348362922668457},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4894760847091675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32595181465148926},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1945616565","https://openalex.org/W2067295501","https://openalex.org/W2127141656","https://openalex.org/W2150769028","https://openalex.org/W2187089797","https://openalex.org/W2749510669","https://openalex.org/W2890964092","https://openalex.org/W2891833136","https://openalex.org/W2951130829","https://openalex.org/W2962788625","https://openalex.org/W2963542245","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2972705840","https://openalex.org/W2981087920","https://openalex.org/W2995181338","https://openalex.org/W3015636705","https://openalex.org/W3024085360","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3027008958","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3154262773","https://openalex.org/W3159481202","https://openalex.org/W3161606033","https://openalex.org/W3197580070","https://openalex.org/W3198694222","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4223655162","https://openalex.org/W4237168004","https://openalex.org/W4285250921","https://openalex.org/W4290995108","https://openalex.org/W4296068987","https://openalex.org/W4297841416","https://openalex.org/W4319862271","https://openalex.org/W4319862473","https://openalex.org/W4321524405","https://openalex.org/W4372259971","https://openalex.org/W4372265824","https://openalex.org/W4372340947","https://openalex.org/W4372346385","https://openalex.org/W4385478165","https://openalex.org/W4385823399","https://openalex.org/W4391021535","https://openalex.org/W4392904263","https://openalex.org/W4392904451","https://openalex.org/W4392904752","https://openalex.org/W4401597866","https://openalex.org/W6638389677","https://openalex.org/W6640425456","https://openalex.org/W6685133223","https://openalex.org/W6769867024","https://openalex.org/W6777776875","https://openalex.org/W6780218876","https://openalex.org/W6810007534","https://openalex.org/W6841559111","https://openalex.org/W6845493640","https://openalex.org/W6849840340","https://openalex.org/W6861105714"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2111874347","https://openalex.org/W2640905660"],"abstract_inverted_index":{"Target-speaker":[0],"speech":[1,9,13,31,118],"processing":[2],"(TS)":[3],"tasks,":[4,99],"such":[5],"as":[6],"target-speaker":[7,60],"automatic":[8],"recognition":[10,109],"(TS-ASR),":[11],"target":[12,121,131],"extraction":[14],"(TSE),":[15],"and":[16,97,184],"personal":[17],"voice":[18],"activity":[19],"detection":[20],"(p-VAD),":[21],"are":[22],"important":[23],"for":[24,51,58,87,93],"extracting":[25],"information":[26],"about":[27],"a":[28,68,78,138,154],"desired":[29],"speaker\u2019s":[30,132],"even":[32],"when":[33],"it":[34,152],"is":[35,82,171],"corrupted":[36],"by":[37],"interfering":[38],"speakers.":[39],"While":[40],"most":[41],"studies":[42],"have":[43],"focused":[44],"on":[45,160,189],"training":[46],"schemes":[47],"or":[48,107],"system":[49],"architectures":[50],"each":[52],"specific":[53],"task,":[54],"the":[55,83,94,120,130,135,144,161,178,185,190],"auxiliary":[56],"network":[57],"embedding":[59,86,187],"cues":[61],"has":[62],"not":[63],"been":[64],"investigated":[65],"comprehensively":[66],"in":[67,134],"unified":[69],"crosstask":[70],"evaluation.":[71],"Therefore,":[72],"this":[73,91],"paper":[74],"aims":[75],"to":[76,157,174],"address":[77],"fundamental":[79],"question:":[80],"what":[81],"preferred":[84],"speaker":[85,103,108,113,122,125,148,168],"TS":[88,162,175],"tasks?":[89],"To":[90,141],"end,":[92],"TS-ASR,":[95],"TSE,":[96],"p-VAD":[98],"we":[100,150],"compare":[101],"pre-trained":[102],"encoders":[104],"(i.e.,":[105],"self-supervised":[106],"models)":[110],"that":[111,167],"compute":[112],"embeddings":[114,126],"from":[115,129],"pre-recorded":[116],"enrollment":[117],"of":[119,137,146],"with":[123],"ideal":[124,147],"derived":[127],"directly":[128],"identity":[133],"form":[136],"one-hot":[139,179],"vector.":[140],"further":[142],"understand":[143],"properties":[145],"embedding,":[149],"optimize":[151],"using":[153],"gradient-based":[155],"approach":[156],"improve":[158],"performance":[159,170],"task.":[163],"Our":[164],"analysis":[165],"reveals":[166],"verification":[169],"somewhat":[172],"unrelated":[173],"task":[176],"performances,":[177],"vector":[180],"outperforms":[181],"enrollment-based":[182],"ones,":[183],"optimal":[186],"depends":[188],"input":[191],"mixture.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}