{"id":"https://openalex.org/W4406859685","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849014","title":"VietSing: A High-quality Vietnamese Singing Voice Corpus","display_name":"VietSing: A High-quality Vietnamese Singing Voice Corpus","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406859685","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849014"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5054242571","display_name":"Vu Minh Duc","orcid":"https://orcid.org/0000-0001-7798-4341"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Minh Vu","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhou Wei","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116046773","display_name":"Binit Bhattarai","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Binit Bhattarai","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044142616","display_name":"Kah Kuan Teh","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kah Kuan Teh","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110125670","display_name":"Tran Huy Dat","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tran Huy Dat","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"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":0.991599977016449,"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":0.991599977016449,"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/T11309","display_name":"Music and Audio Processing","score":0.9715999960899353,"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/T10860","display_name":"Speech and Audio Processing","score":0.9638000130653381,"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":0.9232872724533081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7394940853118896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5988690257072449},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.591549277305603},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5838942527770996},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34089305996894836},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2339385449886322},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06873512268066406}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.9232872724533081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394940853118896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5988690257072449},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.591549277305603},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5838942527770996},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34089305996894836},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2339385449886322},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06873512268066406},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":19,"referenced_works":["https://openalex.org/W2067709094","https://openalex.org/W2747874407","https://openalex.org/W2778460379","https://openalex.org/W3097514409","https://openalex.org/W3150572638","https://openalex.org/W3158762648","https://openalex.org/W3159302906","https://openalex.org/W3165908916","https://openalex.org/W3181854487","https://openalex.org/W4205742757","https://openalex.org/W4296068763","https://openalex.org/W4385823416","https://openalex.org/W4391020683","https://openalex.org/W4391021798","https://openalex.org/W6761725420","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6846351131"],"related_works":["https://openalex.org/W2901286616","https://openalex.org/W2291461084","https://openalex.org/W2050882094","https://openalex.org/W3113733647","https://openalex.org/W4206924063","https://openalex.org/W3042674643","https://openalex.org/W1844055093","https://openalex.org/W61780229","https://openalex.org/W2077055222","https://openalex.org/W2973218968"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3],"comprehensive":[4],"Vietnamese":[5,34,75,118],"dataset":[6,122,138],"designed":[7],"for":[8,19,29,163],"singing":[9,119],"voice":[10],"synthesis":[11],"(SVS).":[12],"While":[13],"there":[14],"are":[15,35,68],"extensive":[16],"datasets":[17],"available":[18,126],"widely":[20],"spoken":[21],"languages":[22,32],"such":[23],"as":[24],"English":[25],"and":[26,45,55,63,77,89,96,114,160],"Chinese,":[27],"resources":[28],"less":[30],"common":[31],"like":[33],"still":[36],"scarce.":[37],"The":[38,121],"dataset,":[39],"VietSing,":[40],"comprises":[41],"high-quality":[42],"audio":[43,158],"recordings":[44],"corresponding":[46,142],"phonetic":[47,61],"annotations,":[48],"meticulously":[49],"curated":[50],"to":[51,70,110,128,136,149],"support":[52],"the":[53,83,90,106,112,137,141,150,153,161],"development":[54],"evaluation":[56,166],"of":[57,74,108,116,152],"SVS":[58,103],"systems.":[59],"Detailed":[60],"transcriptions":[62],"alignment":[64],"with":[65],"musical":[66,97],"scores":[67],"provided":[69],"facilitate":[71],"precise":[72],"modeling":[73],"phonetics":[76],"prosody":[78],"in":[79,93],"song.":[80],"We":[81],"outline":[82],"data":[84],"collection":[85],"process,":[86],"annotation":[87],"methodology,":[88],"challenges":[91],"faced":[92],"ensuring":[94],"linguistic":[95],"accuracy.":[98],"Initial":[99],"experiments":[100],"using":[101],"popular":[102],"model":[104],"demonstrate":[105],"potential":[107],"VietSing":[109],"enhance":[111],"naturalness":[113],"intelligibility":[115],"synthesized":[117],"voices.":[120],"is":[123],"not":[124],"publicly":[125],"due":[127],"licensing":[129,155],"restrictions.":[130],"Interested":[131],"researchers":[132],"can":[133,168],"request":[134],"access":[135],"by":[139],"contacting":[140],"authors.":[143],"Access":[144],"will":[145],"be":[146,169],"granted":[147],"subject":[148],"approval":[151],"appropriate":[154],"agreements.":[156],"Some":[157],"samples":[159],"code":[162],"our":[164],"baseline":[165],"method":[167],"found":[170],"at":[171],"this":[172],"link<sup":[173],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[174],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[175]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
