{"id":"https://openalex.org/W4392903841","doi":"https://doi.org/10.1109/icassp48485.2024.10446032","title":"Boosting Unknown-Number Speaker Separation with Transformer Decoder-Based Attractor","display_name":"Boosting Unknown-Number Speaker Separation with Transformer Decoder-Based Attractor","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903841","doi":"https://doi.org/10.1109/icassp48485.2024.10446032"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5024990167","display_name":"Younglo Lee","orcid":"https://orcid.org/0000-0002-0725-3444"},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Younglo Lee","raw_affiliation_strings":["42dot Inc.,Seoul,Korea","42dot Inc., Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc., Seoul, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051189765","display_name":"Shukjae Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shukjae Choi","raw_affiliation_strings":["42dot Inc.,Seoul,Korea","42dot Inc., Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc., Seoul, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053784244","display_name":"Byeong-Yeol Kim","orcid":"https://orcid.org/0000-0001-6019-5047"},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeong-Yeol Kim","raw_affiliation_strings":["42dot Inc.,Seoul,Korea","42dot Inc., Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc., Seoul, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"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":"Zhong-Qiu Wang","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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,Language Technologies Institute,Pittsburgh,USA","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3629,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92962001,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"446","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9997000098228455,"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/attractor","display_name":"Attractor","score":0.7864032983779907},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7216799855232239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5617161393165588},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5120618939399719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5104352831840515},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.43779346346855164},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42092129588127136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3994000256061554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29275739192962646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27819037437438965}],"concepts":[{"id":"https://openalex.org/C164380108","wikidata":"https://www.wikidata.org/wiki/Q507187","display_name":"Attractor","level":2,"score":0.7864032983779907},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7216799855232239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5617161393165588},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5120618939399719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5104352831840515},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.43779346346855164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42092129588127136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3994000256061554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29275739192962646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27819037437438965},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2760103357","https://openalex.org/W2794289187","https://openalex.org/W2808479354","https://openalex.org/W2891054259","https://openalex.org/W2891405874","https://openalex.org/W2899663614","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2972767900","https://openalex.org/W3015199127","https://openalex.org/W3095082129","https://openalex.org/W3095212884","https://openalex.org/W3096609285","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W3160408143","https://openalex.org/W3161301466","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W4288089799","https://openalex.org/W4296068774","https://openalex.org/W4297841822","https://openalex.org/W4319862481","https://openalex.org/W4366503942","https://openalex.org/W4372271367","https://openalex.org/W4375869348","https://openalex.org/W4385756463","https://openalex.org/W6679434410","https://openalex.org/W6755977528","https://openalex.org/W6757817989","https://openalex.org/W6769627184","https://openalex.org/W6774995033","https://openalex.org/W6779752190","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W3049714198","https://openalex.org/W2960434112","https://openalex.org/W2036805113","https://openalex.org/W2592279130","https://openalex.org/W2049158118","https://openalex.org/W2123827981","https://openalex.org/W4205994410","https://openalex.org/W1499880030","https://openalex.org/W34461864","https://openalex.org/W2181936729"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,22,32,59,107,163],"novel":[3],"speech":[4],"separation":[5],"model":[6,19,28,55,165,174],"designed":[7],"to":[8,122,137,167,189],"separate":[9,168],"mixtures":[10,186],"with":[11,42,97,114,132,162,187],"an":[12,43,85,133],"unknown":[13,44],"number":[14,45],"of":[15,46,63,80],"speakers.":[16,191],"The":[17,91,110,140,172],"proposed":[18,141,173],"stacks":[20],"1)":[21],"dual-path":[23,74,130],"processing":[24,51],"block":[25],"that":[26,39,53],"can":[27,40,54],"spectro-temporal":[29],"patterns,":[30],"2)":[31],"transformer":[33],"decoder-based":[34],"attractor":[35,86],"(TDA)":[36],"calculation":[37],"module":[38],"deal":[41],"speakers,":[47],"and":[48,67,83,153,159,179,184],"3)":[49],"triple-path":[50,125],"blocks":[52,131],"inter-speaker":[56,138],"relations.":[57],"Given":[58],"fixed,":[60],"small":[61],"set":[62],"learned":[64],"speaker":[65,108,115],"queries":[66,82],"the":[68,73,78,98,123,129,144,149],"mixture":[69,99,111],"embedding":[70,100],"produced":[71,117],"by":[72,101,118],"blocks,":[75,126],"TDA":[76],"infers":[77],"relations":[79],"these":[81],"generates":[84],"vector":[87],"for":[88],"each":[89],"speaker.":[90],"estimated":[92],"attractors":[93],"are":[94],"then":[95],"combined":[96],"feature-wise":[102],"linear":[103],"modulation":[104],"conditioning,":[105],"creating":[106],"dimension.":[109],"embedding,":[112],"conditioned":[113],"information":[116],"TDA,":[119],"is":[120],"fed":[121],"final":[124],"which":[127],"augment":[128],"additional":[134],"pathway":[135],"dedicated":[136],"processing.":[139],"approach":[142],"outperforms":[143],"previous":[145],"best":[146],"reported":[147],"in":[148],"literature,":[150],"achieving":[151],"24.0":[152],"23.7":[154],"dB":[155],"\u2206SI-SDR":[156],"on":[157],"WSJ0-2":[158],"3mix":[160],"respectively,":[161],"single":[164],"trained":[166],"2-and":[169],"3-speaker":[170],"mixtures.":[171],"also":[175],"exhibits":[176],"strong":[177],"performance":[178],"generalizability":[180],"at":[181],"counting":[182],"sources":[183],"separating":[185],"up":[188],"5":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}