{"id":"https://openalex.org/W7166875287","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1785","title":"VocalRep: Structure-Aware Vocal Representations for Multimodal Generation","display_name":"VocalRep: Structure-Aware Vocal Representations for Multimodal Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166875287","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1785"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1785","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1785","pdf_url":"https://aclanthology.org/2026.findings-acl.1785.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 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1785.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139772667","display_name":"Da Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Da Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124255404","display_name":"Zhenqiang Weng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenqiang Weng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139792377","display_name":"Tianyu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039455173","display_name":"Gongyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gongyu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030514341","display_name":"Runhua Shi","orcid":"https://orcid.org/0000-0003-4513-1306"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runhua Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139785355","display_name":"Jiahui Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahui Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111268242","display_name":"Chaofan Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaofan Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139752506","display_name":"Wei-Qiang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139783094","display_name":"Zihao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88964097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35850","last_page":"35865"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.14830000698566437,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.14830000698566437,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.1324000060558319,"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/T11309","display_name":"Music and Audio Processing","score":0.09139999747276306,"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/frame","display_name":"Frame (networking)","score":0.28519999980926514},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2759000062942505},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.2639999985694885},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2551000118255615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5501000285148621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41679999232292175},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3133000135421753},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2498999983072281}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1785","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1785","pdf_url":"https://aclanthology.org/2026.findings-acl.1785.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1785","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1785","pdf_url":"https://aclanthology.org/2026.findings-acl.1785.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166875287.pdf","grobid_xml":"https://content.openalex.org/works/W7166875287.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"speech":[1],"and":[2,11,20,49,109,152],"multimodal":[3],"generation":[4,79],"systems,":[5],"such":[6,27],"as":[7],"singing":[8,149],"voice":[9,150],"conversion":[10,151],"audio-driven":[12,153],"lip":[13,154],"synchronization,":[14],"critically":[15],"depend":[16],"on":[17,134],"temporally":[18],"stable":[19],"semantically":[21],"unambiguous":[22],"vocal":[23,55,87,120,130],"representations.In":[24],"practical":[25],"pipelines,":[26],"representations":[28,131],"are":[29],"typically":[30],"derived":[31],"from":[32,89],"music":[33],"source":[34],"separation":[35,58,88],"(MSS)":[36],"applied":[37],"to":[38,104],"mixed":[39],"musical":[40],"recordings.However,":[41],"standard":[42],"MSS":[43],"paradigms":[44],"often":[45,70],"aggregate":[46],"lead":[47,106,129],"vocals":[48],"backing":[50],"harmonies":[51],"into":[52],"a":[53,81,90,99],"single":[54],"stream.Although":[56],"multi-stem":[57],"has":[59],"been":[60],"explored,":[61],"existing":[62],"approaches":[63],"remain":[64],"primarily":[65],"optimized":[66],"for":[67],"signal-level":[68],"reconstruction,":[69],"overlooking":[71],"the":[72],"intricate":[73],"structural":[74],"disentanglement":[75],"required":[76],"by":[77],"downstream":[78,148],"tasks.From":[80],"generation-oriented":[82],"perspective,":[83],"this":[84,94],"motivates":[85],"revisiting":[86],"representation":[91],"learning":[92,101],"standpoint.To":[93],"end,":[95],"we":[96],"propose":[97],"VocalRep,":[98],"structureaware":[100],"framework":[102],"designed":[103],"disentangle":[105],"vocals,":[107],"harmonies,":[108],"instrument":[110],"while":[111],"enforcing":[112],"role":[113],"consistency":[114],"across":[115],"longform":[116],"audio.By":[117],"integrating":[118],"global":[119],"identity":[121],"conditioning":[122],"with":[123],"ranking-based":[124],"objectives,":[125],"Vo-calRep":[126],"extracts":[127],"role-consistent":[128],"without":[132],"relying":[133],"explicit":[135],"pitch":[136],"or":[137],"symbolic":[138],"annotations.Experimental":[139],"results":[140],"demonstrate":[141],"that":[142],"VocalRep":[143],"significantly":[144],"improves":[145],"performance":[146],"in":[147],"synchronization.":[155]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}