{"id":"https://openalex.org/W7130356582","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385266","title":"Improving Multi-Speaker Transcription for Live News Broadcasts With Canary 1B and Pyannote Diarization","display_name":"Improving Multi-Speaker Transcription for Live News Broadcasts With Canary 1B and Pyannote Diarization","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130356582","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385266"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11385266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5126343676","display_name":"Muhammad Rifqi Adli Gumay","orcid":null},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Muhammad Rifqi Adli Gumay","raw_affiliation_strings":["Faculty of Computer Science Universitas,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science Universitas,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120558238","display_name":"Rahmat Bryan Naufal","orcid":null},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Rahmat Bryan Naufal","raw_affiliation_strings":["Faculty of Computer Science Universitas,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science Universitas,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126286769","display_name":"Alvin Xavier Rakha Wardhana","orcid":null},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Alvin Xavier Rakha Wardhana","raw_affiliation_strings":["Faculty of Computer Science Universitas,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science Universitas,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066073372","display_name":"Kurniawati Azizah","orcid":"https://orcid.org/0000-0002-3217-7025"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Kurniawati Azizah","raw_affiliation_strings":["Faculty of Computer Science Universitas,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science Universitas,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I29617571"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.614300012588501,"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":0.614300012588501,"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":0.1632000058889389,"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/T11439","display_name":"Video Analysis and Summarization","score":0.07190000265836716,"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/transcription","display_name":"Transcription (linguistics)","score":0.7473999857902527},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6656000018119812},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6643000245094299},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4603999853134155},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.3619000017642975}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7473999857902527},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6656000018119812},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6643000245094299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6527000069618225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6147000193595886},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3151000142097473},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26179999113082886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11385266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4376857578754425}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3015783745","https://openalex.org/W4385822293","https://openalex.org/W4402111558"],"related_works":[],"abstract_inverted_index":{"Live":[0],"news":[1,149],"programs":[2],"are":[3],"especially":[4],"challenging":[5],"for":[6,147],"Automatic":[7,31],"Transcription":[8],"(AT)":[9],"systems":[10],"as":[11],"they":[12],"contain":[13],"numerous":[14],"and":[15,22,35,73,87,117,143],"intricate":[16],"interactions":[17],"between":[18],"presenters,":[19],"reporters,":[20],"voiceovers":[21],"off-site":[23],"clips.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"investigate":[29],"whether":[30],"Speech":[32],"Recognition":[33],"(ASR),":[34],"instrumental":[36],"time-aligned":[37],"labels":[38],"from":[39,96],"ASR":[40,58],"decoding":[41],"paths,":[42],"can":[43,138],"be":[44],"used":[45],"to":[46,66],"improve":[47,67],"speaker":[48,74],"diarization":[49],"in":[50,64,89],"domain-specific":[51],"data.":[52],"We":[53],"utilize":[54],"NVIDIA's":[55],"Canary":[56,76,129],"1B":[57,77],"model":[59,105,133],"within":[60],"the":[61,90],"WhisperX":[62],"framework":[63],"order":[65],"AT":[68],"performance,":[69],"word":[70],"level":[71],"alignment":[72],"segmentation.":[75],"has":[78],"generally":[79],"shown":[80],"stronger":[81],"performance":[82],"based":[83],"on":[84],"average":[85],"WER":[86],"RTFx":[88],"previous":[91],"evaluation.":[92],"Using":[93],"experimental":[94],"dataset":[95],"an":[97],"English":[98],"broadcast":[99],"with":[100,134],"several":[101],"speakers,":[102],"our":[103,135],"proposed":[104],"achieves":[106],"0%":[107],"Diarization":[108],"Error":[109,114,120],"Rate":[110,115,121],"(DER),":[111],"2.2%":[112],"Word":[113],"(WER),":[116],"0.04%":[118],"Character":[119],"(CER).":[122],"These":[123],"results":[124],"demonstrate":[125],"that":[126],"by":[127],"integrating":[128],"1":[130],"B":[131],"transcription":[132,145],"search-based":[136],"decoder":[137],"provide":[139],"a":[140],"more":[141],"effective":[142],"efficient":[144],"system":[146],"live":[148],"applications.":[150]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-19T00:00:00"}