{"id":"https://openalex.org/W4412888109","doi":"https://doi.org/10.18653/v1/2025.findings-acl.781","title":"STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation","display_name":"STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888109","doi":"https://doi.org/10.18653/v1/2025.findings-acl.781"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.781","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.781","pdf_url":"https://aclanthology.org/2025.findings-acl.781.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.781.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104320351","display_name":"Wenxiang Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxiang Guo","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385138","display_name":"Bowen Zhang","orcid":"https://orcid.org/0000-0002-3581-9476"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103228451","display_name":"Changhao Pan","orcid":"https://orcid.org/0009-0004-6023-1764"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhao Pan","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060739065","display_name":"Zhiyuan Zhu","orcid":"https://orcid.org/0000-0003-1788-9566"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345538","display_name":"Ruiqi Li","orcid":"https://orcid.org/0000-0003-0145-1519"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiqi Li","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"ZheTao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ZheTao Chen","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012923675","display_name":"Wenhao Xu","orcid":"https://orcid.org/0000-0003-1735-3956"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Xu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15081","last_page":"15093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9984999895095825,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9837999939918518,"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":0.9524000287055969,"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/singing","display_name":"Singing","score":0.8013463616371155},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7722671031951904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6837625503540039},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6817532777786255},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.63811194896698},{"id":"https://openalex.org/keywords/stars","display_name":"Stars","score":0.41711729764938354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3958907127380371},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37048470973968506},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3659088611602783},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16252535581588745},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14044097065925598},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06847518682479858},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.0684337317943573},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.05497777462005615}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8013463616371155},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7722671031951904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6837625503540039},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6817532777786255},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.63811194896698},{"id":"https://openalex.org/C150846664","wikidata":"https://www.wikidata.org/wiki/Q7602306","display_name":"Stars","level":2,"score":0.41711729764938354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3958907127380371},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37048470973968506},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3659088611602783},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16252535581588745},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14044097065925598},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06847518682479858},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0684337317943573},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.05497777462005615},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.781","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.781","pdf_url":"https://aclanthology.org/2025.findings-acl.781.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.781","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.781","pdf_url":"https://aclanthology.org/2025.findings-acl.781.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1101031052","display_name":null,"funder_award_id":"U24A20326","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888109.pdf","grobid_xml":"https://content.openalex.org/works/W4412888109.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W2369345767","https://openalex.org/W2299106185"],"abstract_inverted_index":{"Recent":[0],"breakthroughs":[1],"in":[2,135,160],"singing":[3,24,56,164,173],"voice":[4,174],"synthesis":[5],"(SVS)":[6],"have":[7],"heightened":[8],"the":[9,34,49,121,161],"demand":[10],"for":[11,171],"high-quality":[12],"annotated":[13],"datasets,":[14],"yet":[15],"manual":[16],"annotation":[17,25,35,132],"remains":[18],"prohibitively":[19],"labor-intensive":[20],"and":[21,59,77,85,92,106,149],"resource-intensive.Existing":[22],"automatic":[23],"(ASA)":[26],"methods,":[27],"however,":[28],"primarily":[29],"tackle":[30],"isolated":[31],"aspects":[32],"of":[33,163],"pipeline.To":[36],"address":[37],"this":[38],"fundamental":[39],"challenge,":[40],"we":[41],"present":[42],"STARS,":[43],"which":[44],"is,":[45],"to":[46,130],"our":[47],"knowledge,":[48],"first":[50],"unified":[51],"framework":[52,63],"that":[53,139],"simultaneously":[54],"addresses":[55],"transcription,":[57],"alignment,":[58,72],"refined":[60],"style":[61,151],"annotation.Our":[62],"delivers":[64],"comprehensive":[65],"multilevel":[66],"annotations":[67],"encompassing:":[68],"(1)":[69],"precise":[70,150],"phoneme-audio":[71],"(2)":[73],"robust":[74],"note":[75],"transcription":[76],"temporal":[78],"localization,":[79],"(3)":[80],"expressive":[81],"vocal":[82],"technique":[83],"identification,":[84],"(4)":[86],"global":[87],"stylistic":[88],"characterization":[89],"including":[90],"emotion":[91],"pace.The":[93],"proposed":[94],"architecture":[95],"employs":[96],"hierarchical":[97,116],"acoustic":[98,112],"feature":[99],"processing":[100],"across":[101,125],"frame,":[102],"word,":[103],"phoneme,":[104],"note,":[105],"sentence":[107],"levels.The":[108],"novel":[109],"non-autoregressive":[110],"local":[111],"encoders":[113],"enable":[114],"structured":[115],"representation":[117],"learning.Experimental":[118],"validation":[119],"confirms":[120],"framework's":[122],"superior":[123],"performance":[124],"multiple":[126],"evaluation":[127],"dimensions":[128],"compared":[129],"existing":[131],"approaches.Furthermore,":[133],"applications":[134],"SVS":[136],"training":[137],"demonstrate":[138],"models":[140],"utilizing":[141],"STARS-annotated":[142],"data":[143],"achieve":[144],"significantly":[145],"enhanced":[146],"perceptual":[147],"naturalness":[148],"control.This":[152],"work":[153],"not":[154],"only":[155],"overcomes":[156],"critical":[157],"scalability":[158],"challenges":[159],"creation":[162],"datasets":[165],"but":[166],"also":[167],"pioneers":[168],"new":[169],"methodologies":[170],"controllable":[172],"synthesis.Audio":[175],"samples":[176],"are":[177],"available":[178],"at":[179],"https://demo-stars.github.io.":[180]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}