{"id":"https://openalex.org/W4393406769","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482947","title":"M-Diarization: A Myanmar Speaker Diarization using Multi-scale dynamic weights","display_name":"M-Diarization: A Myanmar Speaker Diarization using Multi-scale dynamic weights","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4393406769","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482947"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda60357.2023.10482947","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th 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/I80293557","display_name":"University of Computer Studies Yangon","ror":"https://ror.org/019ad8130","country_code":"MM","type":"education","lineage":["https://openalex.org/I80293557"]}],"countries":["MM"],"is_corresponding":false,"raw_author_name":"Myat Aye Aye Aung","raw_affiliation_strings":["University of Computer Studies, Yangon,Faculty of Computer Science, Natural Language Processing Lab,Yangon,Myanmar","Faculty of Computer Science, Natural Language Processing Lab, University of Computer Studies, Yangon, Yangon, Myanmar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Computer Studies, Yangon,Faculty of Computer Science, Natural Language Processing Lab,Yangon,Myanmar","institution_ids":["https://openalex.org/I80293557"]},{"raw_affiliation_string":"Faculty of Computer Science, Natural Language Processing Lab, University of Computer Studies, Yangon, Yangon, Myanmar","institution_ids":["https://openalex.org/I80293557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038930719","display_name":"Win Pa Pa","orcid":null},"institutions":[{"id":"https://openalex.org/I80293557","display_name":"University of Computer Studies Yangon","ror":"https://ror.org/019ad8130","country_code":"MM","type":"education","lineage":["https://openalex.org/I80293557"]}],"countries":["MM"],"is_corresponding":false,"raw_author_name":"Win Pa Pa","raw_affiliation_strings":["University of Computer Studies, Yangon,Faculty of Computer Science, Natural Language Processing Lab,Yangon,Myanmar","Faculty of Computer Science, Natural Language Processing Lab, University of Computer Studies, Yangon, Yangon, Myanmar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Computer Studies, Yangon,Faculty of Computer Science, Natural Language Processing Lab,Yangon,Myanmar","institution_ids":["https://openalex.org/I80293557"]},{"raw_affiliation_string":"Faculty of Computer Science, Natural Language Processing Lab, University of Computer Studies, Yangon, Yangon, Myanmar","institution_ids":["https://openalex.org/I80293557"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006403566","display_name":"Hay Mar Soe Naing","orcid":"https://orcid.org/0000-0002-3062-2383"},"institutions":[{"id":"https://openalex.org/I80293557","display_name":"University of Computer Studies Yangon","ror":"https://ror.org/019ad8130","country_code":"MM","type":"education","lineage":["https://openalex.org/I80293557"]}],"countries":["MM"],"is_corresponding":false,"raw_author_name":"Hay Mar Soe Naing","raw_affiliation_strings":["University of Computer Studies, Yangon,Faculty of Computer Science, Natural Language Processing Lab,Yangon,Myanmar","Faculty of Computer Science, Natural Language Processing Lab, University of Computer Studies, Yangon, Yangon, Myanmar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Computer Studies, Yangon,Faculty of Computer Science, Natural Language Processing Lab,Yangon,Myanmar","institution_ids":["https://openalex.org/I80293557"]},{"raw_affiliation_string":"Faculty of Computer Science, Natural Language Processing Lab, University of Computer Studies, Yangon, Yangon, Myanmar","institution_ids":["https://openalex.org/I80293557"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I80293557"],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64434536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9944999814033508,"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":0.9768999814987183,"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":0.9596343040466309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7475612163543701},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6673824787139893},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.63338702917099},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5207040905952454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3492179811000824}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9596343040466309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7475612163543701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6673824787139893},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.63338702917099},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5207040905952454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3492179811000824},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda60357.2023.10482947","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2093499222","https://openalex.org/W2150769028","https://openalex.org/W2889203268","https://openalex.org/W2889418727","https://openalex.org/W2997419692","https://openalex.org/W3105031100","https://openalex.org/W3162687954","https://openalex.org/W3203417382","https://openalex.org/W3204593031","https://openalex.org/W3205878676","https://openalex.org/W3212886388","https://openalex.org/W4249179470","https://openalex.org/W4296069155"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"This":[0,267],"paper":[1],"introduces":[2],"M-Diarization":[3,171,290],"dataset":[4,9,30,77,218],"for":[5,54,83,116,194],"Myanmar":[6,72,84],"language.":[7],"The":[8,25,76,208],"contains":[10],"the":[11,81,122,142,184,222,260],"dialog":[12],"of":[13,28,71,136,155,186,206,249,263],"two":[14,204],"speakers":[15,187],"in":[16,80,89,210],"a":[17,51,68,175,226],"meeting,":[18],"live":[19],"interview,":[20],"discussion":[21],"and":[22,43,64,102,110,120,139,165,173,188,219,231,245,253,283],"talk":[23],"show.":[24],"primary":[26],"objective":[27],"this":[29,128,149,211],"is":[31,78,93,257],"to":[32,61,95,118,168,182],"facilitate":[33],"speaker":[34,41,85,90,99,104,132,177,191,196,216],"diarization,":[35],"speech/speaker":[36],"recognition,":[37],"as":[38,40,50,225],"well":[39],"identification":[42],"verification":[44],"tasks.":[45],"Furthermore,":[46],"it":[47],"can":[48],"serve":[49],"valuable":[52],"resource":[53],"various":[55,137],"tasks,":[56],"including":[57],"but":[58],"not":[59],"limited":[60],"dereverberation,":[62],"denoising,":[63],"speech":[65,73,108,112],"enhancement,":[66],"supporting":[67],"wide":[69],"range":[70],"processing":[74],"research.":[75],"applied":[79,151],"study":[82,212],"diarization.":[86],"A":[87,124],"trade-off":[88,129],"diarization":[91,217,223],"systems":[92],"struggled":[94],"achieve":[96],"both":[97],"precise":[98],"turn":[100],"boundaries":[101],"accurate":[103],"identity":[105],"information.":[106],"Short":[107],"segments":[109,135],"overlapped":[111],"that":[113,213],"are":[114,236],"challenging":[115],"machines":[117],"transcribe":[119],"identify":[121],"speaker.":[123],"multi-scale":[125,156,232,264],"strategy":[126],"addresses":[127],"by":[130],"extracting":[131],"features":[133],"from":[134,144],"lengths":[138,162],"subsequently":[140],"integrating":[141],"outcomes":[143],"these":[145],"multiple":[146],"scales.":[147],"In":[148],"paper,":[150],"three":[152],"different":[153,229],"sets":[154],"weight":[157,233,265],"values,":[158],"each":[159,195],"with":[160],"varying":[161],"(5,":[163],"6,":[164],"7":[166],"scales),":[167],"analyze":[169],"diverse":[170],"Datasets":[172],"utilized":[174],"pre-trained":[176],"embedding":[178],"extractor,":[179],"specifically":[180],"TitaNet-L,":[181],"predict":[183],"number":[185],"derive":[189],"average":[190],"representation":[192],"vectors":[193],"at":[197],"every":[198],"scale.":[199],"Each":[200],"scales":[201],"length":[202,230,255],"includes":[203],"types":[205,262],"parameters.":[207],"contribution":[209],"present":[214],"new":[215],"significantly":[220],"improve":[221],"performance":[224],"baseline":[227],"on":[228,275,280,286,289],"values.":[234,266],"There":[235],"six":[237],"parameters":[238],"P1":[239],"(baseline),":[240],"P2,":[241],"P3,":[242],"P4,":[243],"P5":[244],"P6.":[246],"Parameter":[247],"P2":[248],"base":[250],"scale":[251],"0.5s":[252],"shift":[254],"0.25s":[256],"outperformed":[258],"than":[259],"other":[261],"system":[268],"achieves":[269],"6.64%":[270],"Diarization":[271],"Error":[272],"Rate":[273],"(DER)":[274],"3":[276],"hours,":[277],"7.89%":[278],"DER":[279,285],"5":[281],"hours":[282,288],"9.33%":[284],"8":[287],"dataset.":[291]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}