{"id":"https://openalex.org/W6968827537","doi":"https://doi.org/10.5281/zenodo.14877433","title":"Sanidha: A Studio Quality Multi-Modal Dataset for Carnatic Music","display_name":"Sanidha: A Studio Quality Multi-Modal Dataset for Carnatic Music","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6968827537","doi":"https://doi.org/10.5281/zenodo.14877433"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2501.06959","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.06959","pdf_url":"https://arxiv.org/pdf/2501.06959","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"article","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.06959","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Venkatakrishnan Vaidyanathapuram Krishnan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Venkatakrishnan Vaidyanathapuram Krishnan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Noel Alben","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noel Alben","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Anish A. Nair","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anish A. Nair","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Nathaniel Condit-Schultz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathaniel Condit-Schultz","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.4524039,"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/T10860","display_name":"Speech and Audio Processing","score":0.777999997138977,"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/T10860","display_name":"Speech and Audio Processing","score":0.777999997138977,"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/T11309","display_name":"Music and Audio Processing","score":0.15710000693798065,"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":0.033399999141693115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/studio","display_name":"Studio","score":0.6473000049591064},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6119999885559082},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.42289999127388},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.37869998812675476},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.3287999927997589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177000284194946},{"id":"https://openalex.org/C45012715","wikidata":"https://www.wikidata.org/wiki/Q746628","display_name":"Studio","level":2,"score":0.6473000049591064},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4778999984264374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4244999885559082},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3628000020980835},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2501.06959","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.06959","pdf_url":"https://arxiv.org/pdf/2501.06959","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.5281/zenodo.14877433","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877433","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":""}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.06959","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.06959","pdf_url":"https://arxiv.org/pdf/2501.06959","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4986284673213959,"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":{"Music":[0],"source":[1,86,142],"separation":[2,87,143],"demixes":[3],"a":[4,18,63,81,157,173],"piece":[5],"of":[6,35,128,137,164],"music":[7,37,61],"into":[8],"its":[9],"individual":[10],"sound":[11],"sources":[12],"(vocals,":[13],"percussion,":[14],"melodic":[15],"instruments,":[16],"etc.),":[17],"task":[19],"with":[20,66,112,120,168],"no":[21,115],"simple":[22],"mathematical":[23],"solution.":[24],"It":[25],"requires":[26],"deep":[27],"learning":[28],"methods":[29],"involving":[30],"training":[31],"on":[32,145,156],"large":[33],"datasets":[34,43],"isolated":[36],"stems.":[38],"The":[39,162],"most":[40,139],"commonly":[41,140],"available":[42,68,85],"are":[44,170],"made":[45],"from":[46],"commercial":[47],"Western":[48],"music,":[49,107],"limiting":[50],"the":[51,67,77,100,121,129,138,165],"models'":[52],"applications":[53],"to":[54,83,114,154],"non-Western":[55],"genres":[56],"like":[57,89],"Carnatic":[58,60,106,159],"music.":[59],"is":[62],"live":[64],"tradition,":[65],"multi-track":[69,110,160],"recordings":[70,111],"containing":[71],"overlapping":[72],"sounds":[73],"and":[74,91,148],"bleeds":[75],"between":[76],"sources.":[78],"This":[79],"poses":[80],"challenge":[82],"commercially":[84],"models":[88],"Spleeter":[90],"Hybrid":[92],"Demucs.":[93],"In":[94],"this":[95],"work,":[96],"we":[97,124,133],"introduce":[98],"Sanidha,":[99],"first":[101],"open-source":[102],"novel":[103],"dataset1":[104],"for":[105],"offering":[108],"studio-quality,":[109],"minimal":[113],"overlap":[116],"or":[117],"bleed.":[118],"Along":[119],"audio":[122],"files,":[123],"provide":[125],"high-definition":[126],"videos":[127],"artists'":[130],"performances.":[131],"Additionally,":[132],"fine-tuned":[134,166],"Spleeter,":[135],"one":[136],"used":[141],"models,":[144],"our":[146],"dataset":[147],"observed":[149],"improved":[150],"SDR":[151],"performance":[152],"compared":[153],"finetuning":[155],"pre-existing":[158],"dataset.":[161],"outputs":[163],"model":[167],"Sanidha":[169],"evaluated":[171],"through":[172],"listening":[174],"study.":[175]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}