{"id":"https://openalex.org/W4392904047","doi":"https://doi.org/10.1109/icassp48485.2024.10447122","title":"Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models","display_name":"Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904047","doi":"https://doi.org/10.1109/icassp48485.2024.10447122"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://iris.unive.it/bitstream/10278/5080982/1/2403.11706v1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069620223","display_name":"Emilian Postolache","orcid":"https://orcid.org/0000-0002-4785-5204"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Emilian Postolache","raw_affiliation_strings":["Sapienza University of Rome"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032905625","display_name":"Giorgio Mariani","orcid":"https://orcid.org/0000-0002-8135-0330"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giorgio Mariani","raw_affiliation_strings":["Sapienza University of Rome"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085428440","display_name":"Luca Cosmo","orcid":"https://orcid.org/0000-0001-7729-4666"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Cosmo","raw_affiliation_strings":["Ca&#x2019; Foscari University of Venice"],"affiliations":[{"raw_affiliation_string":"Ca&#x2019; Foscari University of Venice","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Queen Mary University of London"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087051832","display_name":"Emanuele Rodol\u00e0","orcid":"https://orcid.org/0000-0003-0091-7241"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Rodol\u00e0","raw_affiliation_strings":["Sapienza University of Rome"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069620223"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":0.6725,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6325298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6980","last_page":"6984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9943000078201294,"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/T10860","display_name":"Speech and Audio Processing","score":0.9562000036239624,"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":0.7887576818466187},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6816800236701965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6631525158882141},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4740985333919525},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44030898809432983},{"id":"https://openalex.org/keywords/joint-probability-distribution","display_name":"Joint probability distribution","score":0.4144356846809387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41166555881500244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3483158349990845},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16343045234680176},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08569777011871338},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08094960451126099}],"concepts":[{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7887576818466187},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6816800236701965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6631525158882141},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4740985333919525},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44030898809432983},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.4144356846809387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41166555881500244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3483158349990845},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16343045234680176},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08569777011871338},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08094960451126099},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unive.it:10278/5080982","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5080982","pdf_url":"https://iris.unive.it/bitstream/10278/5080982/1/2403.11706v1.pdf","source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/93927","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/93927","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:iris.unive.it:10278/5080982","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5080982","pdf_url":"https://iris.unive.it/bitstream/10278/5080982/1/2403.11706v1.pdf","source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319993","display_name":"Leverhulme Trust","ror":"https://ror.org/012mzw131"},{"id":"https://openalex.org/F4320320640","display_name":"Lloyd's Tercentenary Research Foundation","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392904047.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2752796333","https://openalex.org/W2959300817","https://openalex.org/W2963799213","https://openalex.org/W2964058413","https://openalex.org/W2972478942","https://openalex.org/W2998490864","https://openalex.org/W3036167779","https://openalex.org/W4225293699","https://openalex.org/W4225314222","https://openalex.org/W4281661987","https://openalex.org/W4288089799","https://openalex.org/W4318351475","https://openalex.org/W4318719023","https://openalex.org/W4319452539","https://openalex.org/W4362598673","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4380136719","https://openalex.org/W4383047490","https://openalex.org/W4383993968","https://openalex.org/W4392903555","https://openalex.org/W4396877837","https://openalex.org/W4401023775","https://openalex.org/W6763945542","https://openalex.org/W6765775151","https://openalex.org/W6769627184","https://openalex.org/W6774212381","https://openalex.org/W6779823529","https://openalex.org/W6786375611","https://openalex.org/W6838327568","https://openalex.org/W6840815571"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W4321636575","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W2045526782","https://openalex.org/W2741131631","https://openalex.org/W2156919374","https://openalex.org/W1483472507","https://openalex.org/W1984019423","https://openalex.org/W4280588203"],"abstract_inverted_index":{"Multi-Source":[0],"Diffusion":[1],"Models":[2],"(MSDM)":[3],"allow":[4,87],"for":[5,88],"compositional":[6],"musical":[7,36],"generation":[8,100,129],"tasks:":[9],"generating":[10],"a":[11,134],"set":[12],"of":[13,48,84,101,111],"coherent":[14,99],"sources,":[15,33,85],"creating":[16],"accompaniments,":[17],"and":[18,42,46,86,103,125,130],"performing":[19],"source":[20,115],"separation.":[21,116],"Despite":[22],"their":[23],"versatility,":[24],"they":[25,74],"require":[26,70],"estimating":[27],"the":[28,32,44,98,108],"joint":[29],"distribution":[30],"over":[31],"necessitating":[34],"pre-separated":[35],"data,":[37],"which":[38],"is":[39],"rarely":[40],"available,":[41],"fixing":[43],"number":[45,83],"type":[47],"sources":[49,102],"at":[50],"training":[51],"time.":[52],"This":[53],"paper":[54],"generalizes":[55],"MSDM":[56,112],"to":[57,113],"arbitrary":[58,82],"time-domain":[59],"diffusion":[60,120],"models":[61,67,121],"conditioned":[62],"on":[63,77,123],"text":[64],"embeddings.":[65],"These":[66],"do":[68],"not":[69],"separated":[71],"data":[72,136],"as":[73],"are":[75],"trained":[76,122],"mixtures,":[78],"can":[79],"parameterize":[80],"an":[81,94],"rich":[89],"semantic":[90],"control.":[91],"We":[92,117],"propose":[93],"inference":[95],"procedure":[96],"enabling":[97],"accompaniments.":[104],"Additionally,":[105],"we":[106],"adapt":[107],"Dirac":[109],"separator":[110],"perform":[114],"experiment":[118],"with":[119],"Slakh2100":[124],"MTG-Jamendo,":[126],"showcasing":[127],"competitive":[128],"separation":[131],"results":[132],"in":[133],"relaxed":[135],"setting.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
