{"id":"https://openalex.org/W6968650270","doi":"https://doi.org/10.5281/zenodo.14877279","title":"Saraga Audiovisual: A Large Multimodal Open Data Collection for the Analysis of Carnatic Music","display_name":"Saraga Audiovisual: A Large Multimodal Open Data Collection for the Analysis of Carnatic Music","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6968650270","doi":"https://doi.org/10.5281/zenodo.14877279"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877279","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877279","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.14877279","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Adithi Shankar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adithi Shankar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gen\u00eds Plaja-Roglans","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gen\u00eds Plaja-Roglans","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Thomas Nuttall","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Nuttall","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mart\u00edn Rocamora","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mart\u00edn Rocamora","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xavier Serra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Serra","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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44868125,"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/T11309","display_name":"Music and Audio Processing","score":0.9614999890327454,"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":0.9614999890327454,"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":0.01549999974668026,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.00800000037997961,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6729000210762024},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5727999806404114},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4327000081539154},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.37959998846054077},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.33169999718666077},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.2978000044822693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825000286102295},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6729000210762024},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35199999809265137},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.33169999718666077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25589999556541443},{"id":"https://openalex.org/C2780535194","wikidata":"https://www.wikidata.org/wiki/Q309901","display_name":"Open data","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877279","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877279","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.14877279","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877279","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","display_name":"Quality Education","score":0.5327474474906921}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Carnatic":[0,96],"music":[1,9],"is":[2,15,33,115,175],"a":[3,86,126],"style":[4],"of":[5,19,65,95,107,112,118,129,140,160,172],"South":[6],"Indian":[7],"art":[8],"whose":[10],"analysis":[11,32],"using":[12],"computational":[13],"methods":[14],"an":[16],"active":[17],"area":[18],"research":[20,77,179],"in":[21],"Music":[22],"Information":[23],"Research":[24],"(MIR).":[25],"A":[26,109],"core,":[27],"open":[28],"dataset":[29,87,114],"for":[30,121,125,152,178],"such":[31],"the":[34,57,66,116,141,145,153,158,161],"Saraga":[35,58,84,164],"dataset,":[36],"which":[37],"includes":[38,89],"multi-stem":[39],"audio,":[40],"expert":[41],"annotations,":[42],"and":[43,60,91,102,148,170],"accompanying":[44],"metadata.":[45],"However,":[46],"it":[47],"has":[48],"been":[49],"noted":[50],"that":[51,61,88],"there":[52],"are":[53],"several":[54],"limitations":[55],"to":[56,70,73,156],"collections,":[59],"additional":[62],"relevant":[63],"aspects":[64],"tradition":[67],"still":[68],"need":[69],"be":[71],"covered":[72],"facilitate":[74],"musicologically":[75],"important":[76],"lines.":[78],"In":[79],"this":[80,113],"work,":[81],"we":[82],"present":[83],"Audiovisual,":[85,165],"new":[90],"more":[92,103],"diverse":[93],"renditions":[94],"vocal":[97],"performances,":[98],"totalling":[99],"42":[100],"concerts":[101],"than":[104],"60":[105],"hours":[106],"music.":[108],"major":[110],"contribution":[111],"inclusion":[117],"video":[119,146],"recordings":[120],"all":[122],"concerts,":[123],"allowing":[124],"wide":[127],"range":[128],"multimodal":[130],"analyses.":[131],"We":[132],"also":[133],"provide":[134],"high-quality":[135],"human":[136],"pose":[137],"estimation":[138],"data":[139],"musicians":[142],"extracted":[143],"from":[144],"footage,":[147],"perform":[149],"benchmarking":[150],"experiments":[151],"different":[154],"modalities":[155],"validate":[157],"utility":[159],"novel":[162],"collection.":[163],"along":[166],"with":[167],"access":[168],"tools":[169],"results":[171],"our":[173],"experiments,":[174],"made":[176],"available":[177],"purposes.":[180]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
