{"id":"https://openalex.org/W4414448470","doi":"https://doi.org/10.1109/asru65441.2025.11434654","title":"Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder","display_name":"Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4414448470","doi":"https://doi.org/10.1109/asru65441.2025.11434654"},"language":"en","primary_location":{"id":"doi:10.1109/asru65441.2025.11434654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.20474","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100568412","display_name":"Muhammad Shakeel","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Muhammad Shakeel","raw_affiliation_strings":["Honda Research Institute Japan,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan,Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091425252","display_name":"Yui Sudo","orcid":"https://orcid.org/0000-0003-2094-6701"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yui Sudo","raw_affiliation_strings":["Honda Research Institute Japan,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan,Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"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":"Yifan Peng","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/A5069664539","display_name":"Chyi-Jiunn Lin","orcid":"https://orcid.org/0000-0002-2447-9330"},"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":"Chyi-Jiunn Lin","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":"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":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85426735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9947999715805054,"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":0.9947999715805054,"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":0.9609000086784363,"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/leverage","display_name":"Leverage (statistics)","score":0.7432000041007996},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6467000246047974},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.517799973487854},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.48980000615119934},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4729999899864197},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46880000829696655},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4023999869823456},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.385699987411499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8118000030517578},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7432000041007996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.694599986076355},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6467000246047974},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.517799973487854},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46880000829696655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4478999972343445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4185999929904938},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3301999866962433},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2567000091075897},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.25429999828338623}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru65441.2025.11434654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.20474","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.20474","pdf_url":"https://arxiv.org/pdf/2508.20474","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2508.20474","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.20474","pdf_url":"https://arxiv.org/pdf/2508.20474","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.20474","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.20474","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.20474","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.20474","pdf_url":"https://arxiv.org/pdf/2508.20474","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W3212886388","https://openalex.org/W4220731890","https://openalex.org/W4385822353","https://openalex.org/W2962866211","https://openalex.org/W2952218014","https://openalex.org/W4372271367","https://openalex.org/W2963843276","https://openalex.org/W2963477857","https://openalex.org/W3015834770","https://openalex.org/W3094821064","https://openalex.org/W3094831814","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W4285044984","https://openalex.org/W4385822356","https://openalex.org/W4390660238","https://openalex.org/W4400615784","https://openalex.org/W4385822321","https://openalex.org/W3095822285","https://openalex.org/W4392903223","https://openalex.org/W4226098957","https://openalex.org/W3008762051","https://openalex.org/W3032969657","https://openalex.org/W4402112083","https://openalex.org/W4403640448","https://openalex.org/W4403640460","https://openalex.org/W4403640495","https://openalex.org/W4403640476","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4402671610","https://openalex.org/W3197580070","https://openalex.org/W4402112192","https://openalex.org/W4319862255","https://openalex.org/W2995166068","https://openalex.org/W2125336414","https://openalex.org/W2915347754","https://openalex.org/W2067295501","https://openalex.org/W2127851351","https://openalex.org/W3109079702","https://openalex.org/W3196194966","https://openalex.org/W4402116591","https://openalex.org/W2962780374","https://openalex.org/W3216846121","https://openalex.org/W4406458406"],"related_works":[],"abstract_inverted_index":{"This":[0,65],"paper":[1],"presents":[2],"a":[3,8,30,46],"unified":[4],"multi-speaker":[5,23,99],"encoder":[6],"(UME),":[7],"novel":[9],"architecture":[10],"that":[11,86],"jointly":[12],"learns":[13],"representations":[14,39],"for":[15,106],"speaker":[16],"diarization":[17,114],"(SD),":[18],"speech":[19,25,32,81],"separation":[20],"(SS),":[21],"and":[22,98,119,123],"automatic":[24],"recognition":[26],"(ASR)":[27],"tasks":[28],"using":[29],"shared":[31],"foundational":[33],"encoder.":[34],"We":[35],"leverage":[36],"the":[37,70,74,91,110],"hidden":[38],"from":[40,55],"multiple":[41],"layers":[42],"of":[43,117],"UME":[44,87,108],"as":[45],"residual":[47],"weighted-sum":[48],"encoding":[49],"(RWSE)":[50],"to":[51,60,95],"effectively":[52],"use":[53],"information":[54],"different":[56],"semantic":[57],"levels,":[58],"contributing":[59],"bottom-up":[61],"alignment":[62],"between":[63],"tasks.":[64],"joint":[66],"training":[67],"approach":[68],"captures":[69],"inherent":[71],"inter-dependencies":[72],"among":[73],"tasks,":[75],"enhancing":[76],"overall":[77],"performance":[78],"on":[79,101,121],"overlapping":[80],"data.":[82],"Our":[83],"evaluations":[84],"demonstrate":[85],"substantially":[88],"improves":[89],"over":[90],"single-task":[92],"baselines":[93],"dedicated":[94],"SD,":[96,107],"SS,":[97],"ASR":[100],"LibriMix":[102],"evaluation":[103,125],"sets.":[104],"Notably,":[105],"outperforms":[109],"previous":[111],"studies,":[112],"achieving":[113],"error":[115],"rates":[116],"1.37%":[118],"2.29%":[120],"Libri2Mix":[122],"Libri3Mix":[124],"sets,":[126],"respectively.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-09-24T00:00:00"}