{"id":"https://openalex.org/W4408352173","doi":"https://doi.org/10.1109/icassp49660.2025.10887574","title":"TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models","display_name":"TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352173","doi":"https://doi.org/10.1109/icassp49660.2025.10887574"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887574","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/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/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/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/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/A5064238041","display_name":"Old\u0159ich Plchot","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":"Oldrich Plchot","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/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"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":"Shoko Araki","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/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"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":"Jan \u010cernock\u00fd","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"]}]}],"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":1,"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":0.9840999841690063,"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":0.9840999841690063,"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":0.9297999739646912,"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/computer-science","display_name":"Computer science","score":0.7872534990310669},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.727076530456543},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.722701907157898},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.644706666469574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4666231870651245},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4488261342048645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872534990310669},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.727076530456543},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.722701907157898},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.644706666469574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4666231870651245},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4488261342048645},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887574","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":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2078483536","https://openalex.org/W2953190524","https://openalex.org/W2972541922","https://openalex.org/W3006926732","https://openalex.org/W3015636705","https://openalex.org/W3016232124","https://openalex.org/W3024085360","https://openalex.org/W3143843080","https://openalex.org/W3189296823","https://openalex.org/W3197580070","https://openalex.org/W3206189675","https://openalex.org/W3206706278","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226403810","https://openalex.org/W4285250921","https://openalex.org/W4296068815","https://openalex.org/W4296070363","https://openalex.org/W4297841877","https://openalex.org/W4319862271","https://openalex.org/W4319862462","https://openalex.org/W4367597591","https://openalex.org/W4372342485","https://openalex.org/W4385822439","https://openalex.org/W4385822775","https://openalex.org/W4385823373","https://openalex.org/W4391021682","https://openalex.org/W4391021793","https://openalex.org/W4391515560","https://openalex.org/W4392903066","https://openalex.org/W4396833001","https://openalex.org/W4400645798","https://openalex.org/W4401597866","https://openalex.org/W4406461701","https://openalex.org/W6679855610","https://openalex.org/W6777776875","https://openalex.org/W6780218876","https://openalex.org/W6810007534","https://openalex.org/W6856366746"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"models":[3,106],"have":[4,13,23],"significantly":[5],"advanced":[6],"speech":[7,76,87,129],"processing":[8,63],"tasks,":[9],"and":[10,71,136,152],"several":[11],"benchmarks":[12,22],"been":[14],"proposed":[15],"to":[16,93,148],"validate":[17],"their":[18],"effectiveness.":[19,155],"However,":[20],"previous":[21],"primarily":[24],"focused":[25],"on":[26],"single-speaker":[27,120],"scenarios,":[28,110],"with":[29],"less":[30],"exploration":[31],"of":[32,103,132],"target-speaker":[33,62],"tasks":[34,64,147],"in":[35,107],"noisy,":[36],"multi-talker":[37],"conditions\u2014a":[38],"more":[39],"challenging":[40],"yet":[41],"practical":[42],"case.":[43],"In":[44,78],"this":[45],"paper,":[46],"we":[47,140],"introduce":[48],"the":[49,68,75,81,101],"Target-Speaker":[50],"Speech":[51],"Processing":[52],"Universal":[53],"Performance":[54],"Benchmark":[55],"(TS-SUPERB),":[56],"which":[57],"includes":[58],"four":[59],"widely":[60],"recognized":[61],"that":[65,112],"require":[66],"identifying":[67],"target":[69,108,128],"speaker":[70,82,109,134],"extracting":[72],"information":[73,151],"from":[74,85,118],"mixture.":[77],"our":[79],"benchmark,":[80],"embedding":[83],"extracted":[84],"enrollment":[86],"is":[88],"used":[89],"as":[90],"a":[91,125,133],"clue":[92],"condition":[94],"downstream":[95],"models.":[96],"The":[97],"benchmark":[98],"result":[99],"reveals":[100],"importance":[102],"evaluating":[104],"SSL":[105],"demonstrating":[111],"performance":[113],"cannot":[114],"be":[115],"easily":[116],"inferred":[117],"related":[119],"tasks.":[121],"Moreover,":[122],"by":[123],"using":[124],"unified":[126],"SSL-based":[127],"encoder,":[130],"consisting":[131],"encoder":[135],"an":[137],"extractor":[138],"module,":[139],"also":[141],"investigate":[142],"joint":[143],"optimization":[144],"across":[145],"TS":[146],"leverage":[149],"mutual":[150],"demonstrate":[153],"its":[154],"<sup":[156],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}