{"id":"https://openalex.org/W6892454952","doi":"https://doi.org/10.5281/zenodo.10265347","title":"Carnatic Singing Voice Separation Using Cold Diffusion on Training Data With Bleeding","display_name":"Carnatic Singing Voice Separation Using Cold Diffusion on Training Data With Bleeding","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6892454952","doi":"https://doi.org/10.5281/zenodo.10265347"},"language":"en","primary_location":{"id":"pmh:oai:repositori.upf.edu:10230/58188","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/58188","pdf_url":"https://repositori.upf.edu/bitstreams/6a37f229-7892-4f23-ac74-8e1594afe1bf/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"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":"","raw_type":"info:eu-repo/semantics/submittedVersion"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositori.upf.edu/bitstreams/6a37f229-7892-4f23-ac74-8e1594afe1bf/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":"Marius Miron","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marius Miron","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","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":"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":0.4025,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58043077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"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":0.9193999767303467,"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":0.9193999767303467,"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":0.027799999341368675,"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/T11309","display_name":"Music and Audio Processing","score":0.011699999682605267,"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/source-separation","display_name":"Source separation","score":0.7134000062942505},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6947000026702881},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6402999758720398},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5483999848365784},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5361999869346619},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4878000020980835},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4018000066280365},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3944000005722046}],"concepts":[{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7134000062942505},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6947000026702881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6905999779701233},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6265000104904175},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5483999848365784},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5361999869346619},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4657000005245209},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.3427000045776367},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3174000084400177},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:repositori.upf.edu:10230/58188","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/58188","pdf_url":"https://repositori.upf.edu/bitstreams/6a37f229-7892-4f23-ac74-8e1594afe1bf/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"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":"","raw_type":"info:eu-repo/semantics/submittedVersion"},{"id":"doi:10.5281/zenodo.10265347","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265347","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":"pmh:oai:repositori.upf.edu:10230/58188","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/58188","pdf_url":"https://repositori.upf.edu/bitstreams/6a37f229-7892-4f23-ac74-8e1594afe1bf/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"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":"","raw_type":"info:eu-repo/semantics/submittedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W6892454952.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Supervised":[0],"music":[1,38,135],"source":[2,47,152],"separation":[3,70,114,153],"systems":[4],"using":[5],"deep":[6],"learning":[7],"are":[8,30,49,56,86],"trained":[9,155],"by":[10,116],"minimizing":[11],"a":[12,36,90,101,133,164],"loss":[13],"function":[14],"between":[15],"pairs":[16],"of":[17,67,183],"predicted":[18],"separations":[19],"and":[20,33,55,77,82,177],"ground-truth":[21,73],"isolated":[22,28],"sources.":[23],"However,":[24],"open":[25,188],"datasets":[26,45,140],"comprising":[27],"sources":[29],"few,":[31],"small,":[32],"restricted":[34],"to":[35,58,98,121],"few":[37],"styles.":[39],"At":[40],"the":[41,65,72,79,83,95,104,112,125],"same":[42],"time,":[43],"multi-track":[44],"with":[46,107,141,157],"bleeding":[48,76,142],"usually":[50],"found":[51],"larger":[52],"in":[53,181],"size,":[54],"easier":[57],"compile.":[59],"In":[60],"this":[61,148],"work,":[62],"we":[63,110],"address":[64],"task":[66],"singing":[68],"voice":[69],"when":[71],"signals":[74],"have":[75],"only":[78],"target":[80],"vocals":[81,106],"corresponding":[84,105],"mixture":[85,102],"available.":[87],"We":[88,128],"train":[89],"cold":[91],"diffusion":[92],"model":[93],"on":[94,132,147,163,174],"frequency":[96],"domain":[97],"iteratively":[99],"transform":[100],"into":[103],"bleeding.":[108],"Next,":[109],"build":[111],"final":[113],"masks":[115],"clustering":[117],"spectrogram":[118],"bins":[119],"according":[120],"their":[122],"evolution":[123],"along":[124],"transformation":[126],"steps.":[127],"test":[129,166],"our":[130,170],"approach":[131],"Carnatic":[134,165],"scenario":[136],"for":[137],"which":[138],"solely":[139,156],"exist,":[143],"while":[144],"current":[145],"research":[146],"repertoire":[149],"commonly":[150],"uses":[151],"models":[154],"Western":[158],"commercial":[159],"music.":[160],"Our":[161],"evaluation":[162],"set":[167],"shows":[168],"that":[169],"system":[171],"improves":[172],"Spleeter":[173],"interference":[175],"removal":[176],"it":[178],"is":[179,187],"competitive":[180],"terms":[182],"signal":[184],"distortion.":[185],"Code":[186],"sourced":[189]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}