{"id":"https://openalex.org/W4416799163","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249339","title":"VietLyrics: A Large-Scale Dataset and Models for Vietnamese Automatic Lyrics Transcription","display_name":"VietLyrics: A Large-Scale Dataset and Models for Vietnamese Automatic Lyrics Transcription","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799163","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249339"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","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/A5087774518","display_name":"Nguyen Quoc Anh","orcid":"https://orcid.org/0000-0003-4446-3800"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nguyen Quoc Anh","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076449804","display_name":"Bernard Cho Ming Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bernard Cheng","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kelvin Soh","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kelvin Soh","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38655632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"843","last_page":"848"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.942300021648407,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.942300021648407,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.009999999776482582,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.00559999980032444,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.9093999862670898},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.9085999727249146},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7366999983787537},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7285000085830688},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3709000051021576}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.9093999862670898},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9085999727249146},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7366999983787537},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7285000085830688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6365000009536743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5938000082969666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4507000148296356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38850000500679016},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.29580000042915344},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2822999954223633}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2973071600","https://openalex.org/W4372260250","https://openalex.org/W4372260429","https://openalex.org/W4392368946"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Lyrics":[1],"Transcription":[2],"(ALT)":[3],"for":[4,116],"Vietnamese":[5,36,105],"music":[6,106],"presents":[7],"unique":[8],"challenges":[9],"due":[10,22],"to":[11,23,51,88,103],"its":[12],"tonal":[13],"complexity":[14],"and":[15,49,68,99,121],"dialectal":[16],"variations,":[17],"but":[18],"remains":[19],"largely":[20],"unexplored":[21],"the":[24,33,81,111],"lack":[25],"of":[26,43,57,113],"a":[27],"dedicated":[28],"dataset.":[29],"Therefore,":[30],"we":[31,76],"curated":[32],"first":[34],"large-scale":[35],"ALT":[37,91,117],"dataset":[38],"(VietLyrics),":[39],"comprising":[40],"647":[41],"hours":[42],"songs":[44],"with":[45],"line-level":[46],"aligned":[47],"lyrics":[48],"metadata":[50],"address":[52],"these":[53],"issues.":[54],"Our":[55],"evaluation":[56],"current":[58],"ASRbased":[59],"approaches":[60],"reveal":[61],"significant":[62],"limitations,":[63],"including":[64,93],"frequent":[65],"transcription":[66],"errors":[67],"hallucinations":[69],"in":[70,118],"non-vocal":[71],"segments.":[72],"To":[73],"improve":[74],"performance,":[75],"fine-tuned":[77],"Whisper":[78],"models":[79],"on":[80],"VietLyrics":[82,98],"dataset,":[83],"achieving":[84],"superior":[85],"results":[86],"compared":[87],"existing":[89],"multilingual":[90],"systems,":[92],"LyricWhiz.":[94],"We":[95],"publicly":[96],"release":[97],"our":[100],"models,":[101],"aiming":[102],"advance":[104],"computing":[107],"research":[108],"while":[109],"demonstrating":[110],"potential":[112],"this":[114],"approach":[115],"low-resource":[119],"language":[120],"music.":[122]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}
