{"id":"https://openalex.org/W6903359331","doi":"https://doi.org/10.1109/lsp.2025.3590325","title":"Joint Diarization and Separation Using SepFormer With Non-Autoregressive Attractors","display_name":"Joint Diarization and Separation Using SepFormer With Non-Autoregressive Attractors","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W6903359331","doi":"https://doi.org/10.1109/lsp.2025.3590325"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3590325","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3590325","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lsp.2025.3590325","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Magdalena Rybicka","orcid":"https://orcid.org/0000-0002-2413-077X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Magdalena Rybicka","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-2413-077X","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Konrad Kowalczyk","orcid":"https://orcid.org/0000-0002-7834-6920"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]},{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Konrad Kowalczyk","raw_affiliation_strings":["AGH University of Krakow, Krakow, Poland"],"raw_orcid":"https://orcid.org/0000-0002-7834-6920","affiliations":[{"raw_affiliation_string":"AGH University of Krakow, Krakow, Poland","institution_ids":["https://openalex.org/I686019","https://openalex.org/I126596746"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Thomas Thebaud","orcid":"https://orcid.org/0000-0001-8953-7872"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I6059380","display_name":"University of Baltimore","ror":"https://ror.org/024gw2733","country_code":"US","type":"education","lineage":["https://openalex.org/I6059380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Thebaud","raw_affiliation_strings":["CLSP Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-8953-7872","affiliations":[{"raw_affiliation_string":"CLSP Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I6059380"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I6059380","display_name":"University of Baltimore","ror":"https://ror.org/024gw2733","country_code":"US","type":"education","lineage":["https://openalex.org/I6059380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["CLSP Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-4489-5753","affiliations":[{"raw_affiliation_string":"CLSP Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I6059380"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I6059380","display_name":"University of Baltimore","ror":"https://ror.org/024gw2733","country_code":"US","type":"education","lineage":["https://openalex.org/I6059380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Villalba","raw_affiliation_strings":["CLSP Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-9459-8426","affiliations":[{"raw_affiliation_string":"CLSP Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I6059380"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48000819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"2913","last_page":"2917"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8773000240325928,"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":0.8773000240325928,"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":0.08990000188350677,"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/T11448","display_name":"Face recognition and analysis","score":0.005200000014156103,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8553000092506409},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6220999956130981},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.505299985408783},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4846999943256378},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.46050000190734863},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4129999876022339},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4101000130176544}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8553000092506409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246000170707703},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6832000017166138},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6220999956130981},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.505299985408783},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3824999928474426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C164380108","wikidata":"https://www.wikidata.org/wiki/Q507187","display_name":"Attractor","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3590325","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3590325","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lsp.2025.3590325","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3590325","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W3015199127","https://openalex.org/W3025260599","https://openalex.org/W3094831814","https://openalex.org/W3095212884","https://openalex.org/W3163652268","https://openalex.org/W3163903701","https://openalex.org/W3196857193","https://openalex.org/W4296069292","https://openalex.org/W4319862481","https://openalex.org/W4366503942","https://openalex.org/W4390660238","https://openalex.org/W4395471098","https://openalex.org/W4400615784","https://openalex.org/W4401387004","https://openalex.org/W4402112280","https://openalex.org/W6777776875"],"related_works":[],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,62,91,138],"and":[2,63,92,137,148],"speech":[3,37,47,64,93],"separation":[4,38,136],"both":[5,77,135],"aim":[6],"to":[7,73],"track":[8],"speaker":[9,28,90,98],"activity":[10],"in":[11,17,58,76],"multi-speaker":[12],"recordings,":[13],"but":[14],"they":[15],"differ":[16],"their":[18],"granularity.":[19],"Diarization":[20],"provides":[21],"a":[22,27,32,49,84,101,108],"binary":[23],"indication":[24],"of":[25,48,116,132],"whether":[26],"is":[29],"active":[30],"within":[31],"given":[33],"time":[34],"frame,":[35],"whereas":[36],"produces":[39],"individual":[40],"audio":[41],"signals,":[42],"each":[43],"containing":[44],"the":[45,117,145],"isolated":[46],"specific":[50],"speaker.":[51],"Recently,":[52],"there":[53],"has":[54],"been":[55],"growing":[56],"interest":[57],"approaches":[59],"that":[60],"unify":[61],"separation,":[65],"particularly":[66],"those":[67],"leveraging":[68],"neural":[69,86],"models":[70],"trained":[71],"jointly":[72],"enhance":[74],"performance":[75],"tasks.":[78],"In":[79],"this":[80],"letter,":[81],"we":[82],"propose":[83],"single":[85],"model":[87,96],"for":[88,120,134],"joint":[89],"separation.":[94],"Our":[95],"estimates":[97],"representations":[99],"using":[100],"non-autoregressive":[102],"attractor":[103],"generation":[104],"mechanism":[105],"integrated":[106],"into":[107],"modified":[109],"SepFormer":[110],"model.":[111],"We":[112],"present":[113],"two":[114],"variants":[115],"model,":[118],"designed":[119],"scenarios":[121],"with":[122],"sparse":[123],"or":[124],"highly":[125],"overlapping":[126],"speech,":[127],"which":[128],"achieve":[129],"relative":[130],"improvements":[131],"51%":[133],"over":[139],"state-of-the-art":[140],"methods,":[141],"as":[142],"evaluated":[143],"on":[144],"LibriMix,":[146],"LibriheavyMix":[147],"CALLHOME":[149],"datasets.":[150]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}