{"id":"https://openalex.org/W4408347310","doi":"https://doi.org/10.1109/icassp49660.2025.10890041","title":"Investigation of Spatial Self-Supervised Learning and Its Application to Target Speaker Speech Recognition","display_name":"Investigation of Spatial Self-Supervised Learning and Its Application to Target Speaker Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347310","doi":"https://doi.org/10.1109/icassp49660.2025.10890041"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890041","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/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682990","display_name":"Samuele Cornell","orcid":"https://orcid.org/0000-0002-5358-1844"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuele Cornell","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003098968","display_name":"Satoru Fukayama","orcid":"https://orcid.org/0000-0001-6506-2796"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoru Fukayama","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]}],"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9397000074386597,"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":0.9397000074386597,"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":0.9287999868392944,"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":0.8008769750595093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7691987752914429},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6684170961380005},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4354628324508667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4313591420650482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8008769750595093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7691987752914429},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6684170961380005},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4354628324508667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4313591420650482}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890041","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1973787919","https://openalex.org/W1983812858","https://openalex.org/W2143027228","https://openalex.org/W2168273590","https://openalex.org/W2400339399","https://openalex.org/W2563666542","https://openalex.org/W2900212944","https://openalex.org/W2901552243","https://openalex.org/W2902990440","https://openalex.org/W2933708090","https://openalex.org/W2937284863","https://openalex.org/W2962970794","https://openalex.org/W2982840733","https://openalex.org/W3015678657","https://openalex.org/W3015746570","https://openalex.org/W3016244615","https://openalex.org/W3020336359","https://openalex.org/W3081267827","https://openalex.org/W3097263872","https://openalex.org/W3115585868","https://openalex.org/W3163257865","https://openalex.org/W3198425604","https://openalex.org/W4292969786","https://openalex.org/W4297841761","https://openalex.org/W4372271362","https://openalex.org/W4385823318","https://openalex.org/W4388117343","https://openalex.org/W4389315128","https://openalex.org/W4392904741","https://openalex.org/W4402111631","https://openalex.org/W4402112083","https://openalex.org/W4403640427","https://openalex.org/W6640963894","https://openalex.org/W6780218876","https://openalex.org/W6784499681","https://openalex.org/W6852668971"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"In":[0],"this":[1,111,176],"paper,":[2],"we":[3],"investigate":[4,131],"spatial":[5,54],"self-supervised":[6,21,55,137,173],"learning":[7,56,174],"for":[8,57],"target":[9,78],"speaker":[10,86],"speech":[11,59,79],"recognition.":[12],"Neural":[13],"separation":[14,45,74],"models":[15,114,142,167],"can":[16],"be":[17,92],"trained":[18],"in":[19,42,152],"a":[20,30,36,68,124],"manner":[22],"by":[23,94,118,143],"using":[24],"only":[25,103],"multichannel":[26,82],"mixture":[27],"signals.":[28],"Such":[29],"framework":[31],"is":[32],"typically":[33],"based":[34,139,164],"on":[35,50,67,140,147,165],"physics-informed":[37],"generative":[38],"model,":[39],"widely":[40],"studied":[41,117],"blind":[43],"source":[44,73,106],"(BSS).":[46],"Our":[47],"study":[48],"focuses":[49],"the":[51,128,133,153,160],"application":[52],"of":[53,126],"distant":[58],"recognition":[60],"(DSR).":[61],"Multi-talker":[62],"DSR":[63,150],"systems":[64],"often":[65],"rely":[66],"BSS":[69,135,162],"method":[70,184],"called":[71],"guided":[72],"(GSS),":[75],"which":[76],"separates":[77],"utterances":[80],"from":[81,169],"mixtures":[83],"and":[84,136,178,185],"their":[85],"activities.":[87],"Its":[88],"performance,":[89],"however,":[90],"would":[91],"limited":[93],"its":[95],"assumption":[96],"that":[97,159],"each":[98,120],"time-frequency":[99],"(TF)":[100],"bin":[101,122],"contains":[102],"one":[104],"sound":[105],"or":[107],"noise.":[108],"To":[109],"address":[110],"limitation,":[112],"factor":[113,141,166],"have":[115],"been":[116],"assuming":[119],"TF":[121],"as":[123],"sum":[125],"all":[127],"sources.":[129],"We":[130,157],"both":[132],"classic":[134,161],"methods":[138,163],"evaluating":[144],"them":[145],"extensively":[146],"multiple":[148],"different":[149],"scenarios":[151],"CHiME-8":[154],"DASR":[155],"challenge.":[156],"show":[158],"suffer":[168],"initialization":[170],"sensitivity,":[171],"while":[172],"mitigated":[175],"problem":[177],"slightly":[179],"outperformed":[180],"GSS.":[181],"The":[182],"best-performing":[183],"audio":[186],"samples":[187],"are":[188],"available":[189],"online":[190],"at":[191],"https://ybando.jp/projects/icassp2025/.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}