{"id":"https://openalex.org/W7130421337","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385084","title":"Joining Diarization and Multi-Speaker Automatic Speech Recognition with Overlap Handling for Long Conversations","display_name":"Joining Diarization and Multi-Speaker Automatic Speech Recognition with Overlap Handling for Long Conversations","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130421337","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385084"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11385084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385084","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/A5051925641","display_name":"Myat Aye Aye Aung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117845","display_name":"University Of Information Technology","ror":"https://ror.org/03bxja712","country_code":"MM","type":"education","lineage":["https://openalex.org/I4210117845"]}],"countries":["MM"],"is_corresponding":false,"raw_author_name":"Myat Aye Aye Aung","raw_affiliation_strings":["University of Computer Studies,Faculty of Computer Science,Yangon,Myanmar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Computer Studies,Faculty of Computer Science,Yangon,Myanmar","institution_ids":["https://openalex.org/I4210117845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038930719","display_name":"Win Pa Pa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Win Pa Pa","raw_affiliation_strings":["Naypyitaw State Polytechnic University,Faculty of Computing,Naypyitaw,Myanmar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naypyitaw State Polytechnic University,Faculty of Computing,Naypyitaw,Myanmar","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology,Division of Information Science,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Division of Information Science,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.9302999973297119,"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":0.9302999973297119,"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":0.050700001418590546,"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":0.002099999925121665,"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":0.8242999911308289},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7739999890327454},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7031999826431274},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6051999926567078},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5681999921798706},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4032999873161316},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39629998803138733}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8242999911308289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749999761581421},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7739999890327454},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7699000239372253},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7031999826431274},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6051999926567078},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5681999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4449000060558319},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4032999873161316},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.31209999322891235},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11385084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385084","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1556857061","https://openalex.org/W2194775991","https://openalex.org/W2460742184","https://openalex.org/W2612601884","https://openalex.org/W2884797218","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2972949456","https://openalex.org/W3004750774","https://openalex.org/W3008357631","https://openalex.org/W3020336359","https://openalex.org/W3024869864","https://openalex.org/W3097777922","https://openalex.org/W4256161595","https://openalex.org/W4313316127","https://openalex.org/W4389315128","https://openalex.org/W4391892525","https://openalex.org/W4393406769","https://openalex.org/W4415432662"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"in":[4,108,131],"long,":[5,52],"multi-speaker":[6,53,145],"conversations":[7],"is":[8],"challenging":[9],"due":[10],"to":[11,34],"speaker":[12,26,60,96,135],"overlap,":[13,136],"dynamic":[14],"turn-taking,":[15],"and":[16,28,58,81,98,117,123],"complex":[17],"segmentation.":[18],"This":[19],"study":[20],"presents":[21],"an":[22],"integrated":[23],"pipeline":[24,120],"combining":[25],"diarization":[27],"ASR,":[29],"with":[30,133],"explicit":[31],"overlap":[32],"handling":[33],"improve":[35],"transcription":[36],"accuracy.":[37],"Traditional":[38],"ASR":[39,80,85],"systems,":[40],"typically":[41],"designed":[42],"for":[43,143],"single-speaker":[44],"or":[45],"short-duration":[46],"audio,":[47],"often":[48],"perform":[49],"poorly":[50],"on":[51,68,89],"recordings.":[54],"While":[55],"variable":[56],"durations":[57],"unknown":[59],"counts":[61,97],"have":[62],"been":[63],"studied,":[64],"this":[65],"work":[66],"focuses":[67],"evaluating":[69],"multi-scale,":[70],"overlap-aware":[71,141],"segmentation":[72,142],"within":[73],"a":[74,77,82],"pipeline.":[75],"Both":[76],"conformer-based":[78],"baseline":[79],"fine-tuned":[83],"Whisper":[84,115],"are":[86],"assessed.":[87],"Experiments":[88],"the":[90,102,118,138],"Myanmar-language":[91],"M-Diarization":[92],"dataset,":[93],"featuring":[94],"varied":[95],"durations,":[99],"show":[100],"that":[101],"proposed":[103,119],"method":[104],"outperforms":[105],"ASR-only":[106],"baselines:":[107],"7-speaker":[109],"scenarios,":[110],"Conformer":[111],"achieves":[112,121,128],"60.91%":[113],"WER,":[114],"54.90%,":[116],"52.26%":[122],"29.50%,":[124],"respectively.":[125],"Notably,":[126],"it":[127],"significant":[129],"gains":[130],"scenarios":[132],"3.31%":[134],"demonstrating":[137],"effectiveness":[139],"of":[140],"low-resource,":[144],"ASR.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-19T00:00:00"}