{"id":"https://openalex.org/W7108644930","doi":"https://doi.org/10.5281/zenodo.17811570","title":"Leveraging Carnatic live recordings for singing voice separation using regression-guided latent diffusion","display_name":"Leveraging Carnatic live recordings for singing voice separation using regression-guided latent diffusion","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108644930","doi":"https://doi.org/10.5281/zenodo.17811570"},"language":"en","primary_location":{"id":"pmh:oai:repositori-api.upf.edu:10230/71153","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/71153","pdf_url":"https://repositori.upf.edu/bitstreams/6ed89b21-c881-466e-b1e5-611568b6dd8a/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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositori.upf.edu/bitstreams/6ed89b21-c881-466e-b1e5-611568b6dd8a/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":"Xavier Serra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","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":[]}],"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":0.52179672,"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":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.19200000166893005,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.19200000166893005,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.15360000729560852,"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":0.14180000126361847,"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/singing","display_name":"Singing","score":0.6485999822616577},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6136000156402588},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5813999772071838},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4936000108718872},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.45010000467300415},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4140999913215637},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.36970001459121704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523999810218811},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6485999822616577},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6136000156402588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5885000228881836},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5813999772071838},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2778473898","wikidata":"https://www.wikidata.org/wiki/Q2145110","display_name":"Repertoire","level":2,"score":0.26919999718666077}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:repositori-api.upf.edu:10230/71153","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/71153","pdf_url":"https://repositori.upf.edu/bitstreams/6ed89b21-c881-466e-b1e5-611568b6dd8a/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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:doi:10.5281/zenodo.17706604","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"ConferencePaper"},{"id":"doi:10.5281/zenodo.17811570","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811570","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-api.upf.edu:10230/71153","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/71153","pdf_url":"https://repositori.upf.edu/bitstreams/6ed89b21-c881-466e-b1e5-611568b6dd8a/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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7108644930.pdf","grobid_xml":"https://content.openalex.org/works/W7108644930.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Score-based":[0],"diffusion":[1,92,134,170],"models":[2],"have":[3,81],"demonstrated":[4],"promise":[5],"to":[6,58,94],"separate":[7],"individual":[8],"sources":[9,80],"from":[10,85],"music":[11,68],"mixture":[12],"signals":[13],"in":[14,127],"a":[15,22,67,90,108,114,145],"generative":[16,56],"fashion,":[17],"paving":[18],"the":[19,53,103,123,128,133,154,166],"way":[20],"for":[21,27,42,64,70,149,175],"new":[23],"class":[24],"of":[25,55,74,98,125,153,168],"solutions":[26],"this":[28,49],"challenging":[29],"task.":[30],"However,":[31],"existing":[32],"works":[33],"rely":[34],"on":[35,102,144],"clean":[36],"multi-stem":[37,75],"data,":[38],"which":[39,71],"is":[40],"scarce":[41],"several":[43],"repertoires,":[44],"consequently":[45],"compromising":[46],"generalization.":[47],"In":[48],"work,":[50],"we":[51,121],"explore":[52],"potential":[54,167],"modeling":[57],"perform":[59,95],"weakly-supervised":[60],"singing":[61],"voice":[62],"separation":[63,97],"Carnatic":[65,99],"Music,":[66],"repertoire":[69],"large":[72],"quantities":[73],"recordings":[76],"with":[77,172],"bleeding":[78,126],"between":[79],"been":[82],"directly":[83],"collected":[84],"live":[86],"performances.":[87],"We":[88],"pre-train":[89],"latent":[91,146,169],"model":[93,135],"preliminary":[96,129],"vocals":[100],"conditioned":[101],"corresponding":[104],"mixture.":[105],"Then,":[106],"through":[107],"separately":[109],"trained":[110],"regressor":[111],"-":[112,120],"using":[113,156],"clean,":[115],"smaller,":[116],"and":[117,131,162],"out-of-domain":[118],"dataset":[119],"estimate":[122],"level":[124],"separations":[130],"guide":[132],"toward":[136],"generating":[137],"cleaner":[138],"samples.":[139],"Albeit":[140],"introducing":[141],"artifacts,":[142],"operating":[143],"space":[147],"allows":[148],"an":[150],"efficient":[151],"development":[152],"system":[155],"limited":[157],"computational":[158],"resources.":[159],"The":[160],"objective":[161],"perceptual":[163],"evaluations":[164],"show":[165],"together":[171],"regression":[173],"guidance":[174],"weekly-supervised":[176],"separation.":[177]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-05T00:00:00"}