{"id":"https://openalex.org/W4408353771","doi":"https://doi.org/10.1109/icassp49660.2025.10890124","title":"VoxVietnam: a Large-Scale Multi-Genre Dataset for Vietnamese Speaker Recognition","display_name":"VoxVietnam: a Large-Scale Multi-Genre Dataset for Vietnamese Speaker Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353771","doi":"https://doi.org/10.1109/icassp49660.2025.10890124"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5111016568","display_name":"Hoang Vu","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hoang Long Vu","raw_affiliation_strings":["Hanoi University of Science and Technology,Hanoi,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114218708","display_name":"Phuong Tuan Dat","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phuong Tuan Dat","raw_affiliation_strings":["Hanoi University of Science and Technology,Hanoi,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071444075","display_name":"Pham Thi Thao Nhi","orcid":"https://orcid.org/0000-0003-4118-8479"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Pham Thao Nhi","raw_affiliation_strings":["Hanoi University of Science and Technology,Hanoi,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nguyen Song Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen Song Hao","raw_affiliation_strings":["Hanoi University of Science and Technology,Hanoi,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061874771","display_name":"Nguyen Thi Thu Trang","orcid":"https://orcid.org/0000-0002-3833-1580"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen Thi Thu Trang","raw_affiliation_strings":["Hanoi University of Science and Technology,Hanoi,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02644134,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9933000206947327,"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":0.9933000206947327,"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":0.9616000056266785,"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/vietnamese","display_name":"Vietnamese","score":0.8299627900123596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7405534982681274},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6455461978912354},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5861261487007141},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5779786109924316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39727258682250977},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36205658316612244},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10947653651237488},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05194205045700073}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8299627900123596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405534982681274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6455461978912354},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5861261487007141},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5779786109924316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39727258682250977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36205658316612244},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10947653651237488},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05194205045700073},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":25,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2593116425","https://openalex.org/W2696967604","https://openalex.org/W2808631503","https://openalex.org/W2963307811","https://openalex.org/W2969985801","https://openalex.org/W2981087920","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3097741049","https://openalex.org/W3134385809","https://openalex.org/W3196523535","https://openalex.org/W3196974791","https://openalex.org/W3209984917","https://openalex.org/W4206908380","https://openalex.org/W4283072473","https://openalex.org/W4312321798","https://openalex.org/W4321780088","https://openalex.org/W4385822285","https://openalex.org/W4385823030","https://openalex.org/W4392904414","https://openalex.org/W4392931137","https://openalex.org/W4402112137","https://openalex.org/W6688816777","https://openalex.org/W6750665317"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"Recent":[0],"research":[1],"in":[2,18,26,39,50,110,132],"speaker":[3,34,64,133],"recognition":[4,35,65,134],"aims":[5],"to":[6,10,77,98,124],"address":[7],"vulnerabilities":[8],"due":[9],"variations":[11],"between":[12],"enrolment":[13],"and":[14,73,105,135],"test":[15],"utterances,":[16],"particularly":[17],"the":[19,23,58,91,95,114,117,126,129,136,140],"multi-genre":[20,51,60,96,130,146],"phenomenon":[21,97,131],"where":[22],"utterances":[24,69],"are":[25,36,122],"different":[27],"speech":[28],"genres.":[29],"Previous":[30],"resources":[31],"for":[32,62,145],"Vietnamese":[33,63],"either":[37],"limited":[38],"size":[40],"or":[41],"do":[42],"not":[43],"focus":[44],"on":[45,81,101],"genre":[46],"diversity,":[47],"leaving":[48],"studies":[49],"effects":[52],"unexplored.":[53],"This":[54],"paper":[55],"introduces":[56],"VoxVietnam,":[57],"first":[59],"dataset":[61,80,142],"with":[66],"over":[67],"187,000":[68],"from":[70,85],"1,406":[71],"speakers":[72],"an":[74],"automated":[75],"pipeline":[76],"construct":[78],"a":[79,82,102,107],"large":[83],"scale":[84],"public":[86],"sources.":[87],"Our":[88,120],"experiments":[89,121],"show":[90],"challenges":[92,127],"posed":[93],"by":[94],"models":[99],"trained":[100],"single-genre":[103],"dataset,":[104],"demonstrate":[106],"significant":[108],"increase":[109],"performance":[111,137],"upon":[112],"incorporating":[113],"VoxVietnam":[115],"into":[116],"training":[118],"process.":[119],"conducted":[123],"study":[125],"of":[128],"gain":[138],"when":[139],"proposed":[141],"is":[143],"used":[144],"training.":[147]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
