{"id":"https://openalex.org/W7148462449","doi":"https://doi.org/10.1109/asru65441.2025.11434778","title":"Can We Really Repurpose Multi-Speaker ASR Corpus for Speaker Diarization?","display_name":"Can We Really Repurpose Multi-Speaker ASR Corpus for Speaker Diarization?","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148462449","doi":"https://doi.org/10.1109/asru65441.2025.11434778"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434778","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":"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/A5132812842","display_name":"Shota Horiguchi","orcid":null},"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"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132792346","display_name":"Naohiro Tawara","orcid":null},"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"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naohiro Tawara","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"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"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Ashihara","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132803906","display_name":"Atsushi Ando","orcid":null},"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"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132829315","display_name":"Marc Delcroix","orcid":null},"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"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT, Inc,Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Inc,Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5132812842"],"corresponding_institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87568125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9478999972343445,"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":0.9478999972343445,"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":0.00989999994635582,"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/T10028","display_name":"Topic Modeling","score":0.0032999999821186066,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.7258999943733215},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6367999911308289},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5982999801635742},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.429500013589859},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41600000858306885},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.3790999948978424},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34540000557899475},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605999708175659},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7258999943733215},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6808000206947327},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6367999911308289},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5982999801635742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4984999895095825},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4002000093460083},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31029999256134033},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434778","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6215388774871826,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2083751884","https://openalex.org/W2175298729","https://openalex.org/W2747874407","https://openalex.org/W2884797218","https://openalex.org/W2891054259","https://openalex.org/W2954930777","https://openalex.org/W2972449503","https://openalex.org/W2972949456","https://openalex.org/W2981087920","https://openalex.org/W3020336359","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3038871978","https://openalex.org/W3097263872","https://openalex.org/W3097700828","https://openalex.org/W3163903701","https://openalex.org/W3178462146","https://openalex.org/W3196117288","https://openalex.org/W3196595845","https://openalex.org/W3196857193","https://openalex.org/W3200796884","https://openalex.org/W3207834622","https://openalex.org/W4220731890","https://openalex.org/W4224920409","https://openalex.org/W4224939064","https://openalex.org/W4296069335","https://openalex.org/W4297841362","https://openalex.org/W4372259977","https://openalex.org/W4372267289","https://openalex.org/W4385822353","https://openalex.org/W4385822356","https://openalex.org/W4385823318","https://openalex.org/W4389315116","https://openalex.org/W4389315122","https://openalex.org/W4389315124","https://openalex.org/W4390660238","https://openalex.org/W4392904263","https://openalex.org/W4402111631","https://openalex.org/W4402111801","https://openalex.org/W4402111989","https://openalex.org/W4402112005","https://openalex.org/W4402112406","https://openalex.org/W4403640460","https://openalex.org/W4408352169","https://openalex.org/W4411276034","https://openalex.org/W4415433617"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"speaker":[1,8],"diarization":[2,60,74,115],"is":[3],"widely":[4],"used":[5],"for":[6,16,36],"overlapaware":[7],"diarization,":[9],"but":[10,121],"it":[11],"requires":[12],"large":[13,23],"multi-speaker":[14,37],"datasets":[15,24,44],"training.":[17],"To":[18],"meet":[19],"this":[20,63],"data":[21,87],"requirement,":[22],"are":[25],"often":[26,45],"constructed":[27],"by":[28],"combining":[29],"multiple":[30],"corpora,":[31],"including":[32],"those":[33],"originally":[34],"designed":[35],"automatic":[38],"speech":[39],"recognition":[40],"(ASR).":[41],"However,":[42],"ASR":[43,123],"feature":[46],"loosely":[47],"defined":[48],"segment":[49],"boundaries":[50,108],"that":[51,67,83],"do":[52],"not":[53,113],"align":[54],"with":[55,88,105,127],"the":[56,73],"stricter":[57],"conventions":[58],"of":[59],"benchmarks.":[61],"In":[62],"work,":[64],"we":[65],"show":[66],"such":[68],"boundary":[69,90],"looseness":[70],"significantly":[71],"impacts":[72],"error":[75],"rate,":[76],"reducing":[77],"evaluation":[78],"reliability.":[79],"We":[80],"also":[81,122],"reveal":[82],"models":[84],"trained":[85],"on":[86],"varying":[89],"precision":[91],"tend":[92],"to":[93,98],"learn":[94],"dataset-specific":[95],"looseness,":[96],"leading":[97],"poor":[99],"generalization":[100],"across":[101],"out-of-domain":[102],"datasets.":[103],"Training":[104],"standardized":[106],"tight":[107],"via":[109],"forced":[110],"alignment":[111],"improves":[112],"only":[114],"performance,":[116],"especially":[117],"in":[118],"streaming":[119],"scenarios,":[120],"performance":[124],"when":[125],"combined":[126],"simple":[128],"post-processing.":[129]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}