{"id":"https://openalex.org/W4390660238","doi":"https://doi.org/10.1109/taslp.2024.3350887","title":"TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings","display_name":"TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390660238","doi":"https://doi.org/10.1109/taslp.2024.3350887"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3350887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3350887","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5064522438","display_name":"Christoph Boeddeker","orcid":"https://orcid.org/0000-0002-8701-1567"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christoph Boeddeker","raw_affiliation_strings":["Paderborn University, Paderborn, Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048730867","display_name":"Aswin Shanmugam Subramanian","orcid":"https://orcid.org/0000-0003-4446-001X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswin Shanmugam Subramanian","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University, Paderborn, Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064522438"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":8.2687,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97871143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"1185","last_page":"1197"},"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":0.9998999834060669,"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":0.9987000226974487,"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-diarisation","display_name":"Speaker diarisation","score":0.8915554285049438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7405001521110535},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6737536787986755},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5836337804794312},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5721368789672852},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5355545878410339},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48800721764564514},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4747222661972046},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44369128346443176},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43117576837539673},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.42436307668685913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34874218702316284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33677738904953003},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1837868094444275},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10770192742347717},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08875289559364319},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07557833194732666}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8915554285049438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405001521110535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6737536787986755},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5836337804794312},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5721368789672852},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5355545878410339},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48800721764564514},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4747222661972046},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44369128346443176},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43117576837539673},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.42436307668685913},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34874218702316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33677738904953003},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1837868094444275},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10770192742347717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08875289559364319},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07557833194732666},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3350887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3350887","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5772014519","display_name":null,"funder_award_id":"448568305","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W2012910847","https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2150769028","https://openalex.org/W2154741421","https://openalex.org/W2164502538","https://openalex.org/W2168729028","https://openalex.org/W2293634267","https://openalex.org/W2398042854","https://openalex.org/W2559260703","https://openalex.org/W2749510669","https://openalex.org/W2890964092","https://openalex.org/W2892163332","https://openalex.org/W2900212944","https://openalex.org/W2938646939","https://openalex.org/W2962780374","https://openalex.org/W2972449503","https://openalex.org/W2972949456","https://openalex.org/W2973062255","https://openalex.org/W2995181338","https://openalex.org/W2997419692","https://openalex.org/W3015843733","https://openalex.org/W3016131876","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3024085360","https://openalex.org/W3025260599","https://openalex.org/W3094831814","https://openalex.org/W3095212884","https://openalex.org/W3105031100","https://openalex.org/W3119308075","https://openalex.org/W3161590371","https://openalex.org/W3163903701","https://openalex.org/W3171278394","https://openalex.org/W3182358018","https://openalex.org/W3185109982","https://openalex.org/W3195050710","https://openalex.org/W3196708637","https://openalex.org/W3198694222","https://openalex.org/W3204618061","https://openalex.org/W3209984917","https://openalex.org/W3210390090","https://openalex.org/W3210739676","https://openalex.org/W3213661887","https://openalex.org/W4225661121","https://openalex.org/W4226390724","https://openalex.org/W4226491018","https://openalex.org/W4283014282","https://openalex.org/W4296069268","https://openalex.org/W4297841603","https://openalex.org/W4297841708","https://openalex.org/W4319862481","https://openalex.org/W4372259977","https://openalex.org/W4372346876","https://openalex.org/W4385823318","https://openalex.org/W6631362777","https://openalex.org/W6713311039","https://openalex.org/W6744711567","https://openalex.org/W6745136726","https://openalex.org/W6753842161","https://openalex.org/W6766380642","https://openalex.org/W6803260387"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W4406496871","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"Since":[0],"diarization":[1,32,120],"and":[2,86,112],"source":[3,70],"separation":[4],"of":[5,51,119],"meeting":[6,104],"data":[7,105],"are":[8,40],"closely":[9],"related":[10],"tasks,":[11],"we":[12],"here":[13],"propose":[14],"an":[15],"approach":[16],"to":[17,115,122],"perform":[18],"the":[19,26,44,102,117,123],"two":[20],"objectives":[21],"jointly.":[22],"It":[23],"builds":[24],"upon":[25],"target-speaker":[27],"voice":[28],"activity":[29,48,59],"detection":[30],"(TS-VAD)":[31],"approach,":[33],"which":[34],"assumes":[35],"that":[36,56],"initial":[37],"speaker":[38,47,58],"embeddings":[39],"available.":[41],"We":[42,108],"replace":[43],"final":[45],"combined":[46],"estimation":[49],"network":[50,55],"TS-VAD":[52],"with":[53],"a":[54,62,94],"produces":[57],"estimates":[60],"at":[61],"time-frequency":[63],"resolution.":[64],"Those":[65],"act":[66],"as":[67],"masks":[68],"for":[69,84],"extraction,":[71],"either":[72],"via":[73,76],"masking":[74],"or":[75],"beamforming.":[77],"The":[78],"technique":[79],"can":[80],"be":[81],"applied":[82],"both":[83,91],"single-channel":[85],"multi-channel":[87],"input":[88],"and,":[89],"in":[90],"cases,":[92],"achieves":[93],"new":[95],"state-of-the-art":[96],"word":[97],"error":[98],"rate":[99],"(WER)":[100],"on":[101],"LibriCSS":[103],"recognition":[106],"task.":[107],"further":[109],"compute":[110],"speaker-aware":[111],"speaker-agnostic":[113],"WERs":[114],"isolate":[116],"contribution":[118],"errors":[121],"overall":[124],"WER":[125],"performance.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}