{"id":"https://openalex.org/W4412944920","doi":"https://doi.org/10.18653/v1/2025.acl-long.899","title":"DNCASR: End-to-End Training for Speaker-Attributed ASR","display_name":"DNCASR: End-to-End Training for Speaker-Attributed ASR","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944920","doi":"https://doi.org/10.18653/v1/2025.acl-long.899"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.899","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.899","pdf_url":"https://aclanthology.org/2025.acl-long.899.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.899.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102762683","display_name":"Xianrui Zheng","orcid":"https://orcid.org/0000-0002-1784-7393"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianrui Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phil Woodland","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18369","last_page":"18383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9940000176429749,"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":0.9940000176429749,"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/T12031","display_name":"Speech and dialogue systems","score":0.9760000109672546,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9287999868392944,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7630703449249268},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6866114139556885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6740838289260864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5513439774513245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23515215516090393}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7630703449249268},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6866114139556885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6740838289260864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5513439774513245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23515215516090393},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.899","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.899","pdf_url":"https://aclanthology.org/2025.acl-long.899.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.899","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.899","pdf_url":"https://aclanthology.org/2025.acl-long.899.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944920.pdf","grobid_xml":"https://content.openalex.org/works/W4412944920.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W4404782863"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"DNCASR,":[3],"a":[4,63,68,104,128],"novel":[5],"endto-end":[6],"trainable":[7],"system":[8,57,106],"designed":[9],"for":[10],"joint":[11],"neural":[12],"speaker":[13,35,87,114],"clustering":[14],"and":[15,37,115],"automatic":[16],"speech":[17,76],"recognition":[18],"(ASR),":[19],"enabling":[20],"speaker-attributed":[21,48,122],"transcription":[22],"of":[23,51,86],"long":[24],"multi-party":[25],"meetings.DNCASR":[26],"uses":[27],"two":[28,43],"separate":[29],"encoders":[30],"to":[31,46,58,119],"independently":[32],"encode":[33],"global":[34],"characteristics":[36],"local":[38],"waveform":[39],"information,":[40],"along":[41],"with":[42],"linked":[44,52],"decoders":[45,53],"generate":[47],"transcriptions.The":[49],"use":[50],"allows":[54],"the":[55,81,84,93,99,113,121,133],"entire":[56],"be":[59],"jointly":[60,100],"trained":[61,101],"under":[62],"unified":[64],"loss":[65],"function.By":[66],"employing":[67],"serialised":[69],"training":[70],"approach,":[71],"DNCASR":[72,102,126],"effectively":[73],"addresses":[74],"overlapping":[75,90],"in":[77,89],"real-world":[78],"meetings,":[79],"where":[80],"link":[82],"improves":[83],"prediction":[85],"indices":[88],"segments.Experiments":[91],"on":[92,132],"AMI-MDM":[94,134],"meeting":[95],"corpus":[96],"demonstrate":[97],"that":[98,107],"outperforms":[103],"parallel":[105],"does":[108],"not":[109],"have":[110],"links":[111],"between":[112],"ASR":[116],"decoders.Using":[117],"cpWER":[118],"measure":[120],"word":[123],"error":[124],"rate,":[125],"achieves":[127],"9.0%":[129],"relative":[130],"reduction":[131],"Eval":[135],"set.":[136]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}