{"id":"https://openalex.org/W7077907004","doi":"https://doi.org/10.5281/zenodo.16955817","title":"SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning","display_name":"SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W7077907004","doi":"https://doi.org/10.5281/zenodo.16955817"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.16955817","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16955817","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.16955817","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chopra, Anuradha","orcid":null},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chopra, Anuradha","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Roy, Abhinaba","orcid":null},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Roy, Abhinaba","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":null,"display_name":"Herremans, Dorien","orcid":null},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Herremans, Dorien","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41918058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6851000189781189,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6851000189781189,"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/T13067","display_name":"Geological Modeling and Analysis","score":0.028699999675154686,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":0.017500000074505806,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7935000061988831},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6348000168800354},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6146000027656555},{"id":"https://openalex.org/keywords/pop-music-automation","display_name":"Pop music automation","score":0.5228000283241272},{"id":"https://openalex.org/keywords/chaining","display_name":"Chaining","score":0.4339999854564667},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.42289999127388},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.3653999865055084},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3393000066280365}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7935000061988831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404999732971191},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6348000168800354},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6146000027656555},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.5228000283241272},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5213000178337097},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42820000648498535},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.42289999127388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3684000074863434},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3375999927520752},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3122999966144562},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C114611597","wikidata":"https://www.wikidata.org/wiki/Q373342","display_name":"Popular music","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C91557362","wikidata":"https://www.wikidata.org/wiki/Q16254165","display_name":"Music and artificial intelligence","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C178884764","wikidata":"https://www.wikidata.org/wiki/Q510293","display_name":"Musical acoustics","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.16955817","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16955817","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.16955817","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16955817","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7949761152267456,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Detailed":[0],"captions":[1,112,165],"that":[2,32,73,173],"accurately":[3],"reflect":[4],"the":[5,102,121,133,141,145,180,185],"characteristics":[6],"of":[7,91,123,184],"a":[8,26,70,136,156],"music":[9,13,20,28,38,83,115,129,152,158,167],"piece":[10],"can":[11],"enrich":[12],"databases":[14],"and":[15,49,166,182],"drive":[16],"forward":[17],"research":[18],"in":[19,162,176],"AI.":[21],"This":[22,105],"paper":[23],"intro-":[24],"duces":[25],"multi-task":[27],"captioning":[29,103],"model,":[30,142],"SonicVerse,":[31],"integrates":[33],"caption":[34],"generation":[35,122],"with":[36,151],"auxiliary":[37,87],"feature":[39,159,168],"detection":[40],"tasks":[41],"such":[42],"as":[43,52,60,62],"key":[44,67],"detection,":[45,48],"vo-":[46],"cals":[47],"more,":[50],"so":[51],"to":[53,100],"directly":[54,119],"capture":[55],"both":[56],"low-level":[57],"acoustic":[58],"details":[59],"well":[61],"high-level":[63],"musical":[64],"attributes.":[65],"The":[66,89],"contribution":[68],"is":[69],"projection-based":[71],"architecture":[72],"transforms":[74],"audio":[75],"input":[76],"into":[77,97],"language":[78,98],"tokens,":[79,99],"while":[80],"simultaneously":[81],"detecting":[82],"features":[84,153,175],"through":[85],"dedicated":[86],"heads.":[88],"outputs":[90,134],"these":[92],"heads":[93],"are":[94],"also":[95,118],"projected":[96],"enhance":[101],"input.":[104],"framework":[106],"not":[107],"only":[108],"produces":[109],"rich,":[110],"descriptive":[111],"for":[113,127],"short":[114],"fragments":[116],"but":[117],"enables":[120],"detailed":[124],"time-informed":[125],"descriptions":[126],"longer":[128],"pieces,":[130],"by":[131,148],"chaining":[132],"using":[135,154],"large-language":[137],"model.":[138],"To":[139],"train":[140],"we":[143],"extended":[144],"MusicBench":[146],"dataset":[147],"annotating":[149],"it":[150],"MIRFLEX,":[155],"modular":[157],"extractor,":[160],"resulting":[161],"paired":[163],"audio,":[164],"data.":[169],"Experimental":[170],"results":[171],"show":[172],"incorporating":[174],"this":[177],"way":[178],"improves":[179],"quality":[181],"detail":[183],"generated":[186],"captions.":[187]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
