{"id":"https://openalex.org/W6968560801","doi":"https://doi.org/10.5281/zenodo.14877509","title":"Unsupervised Composable Representations for Audio","display_name":"Unsupervised Composable Representations for Audio","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6968560801","doi":"https://doi.org/10.5281/zenodo.14877509"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877509","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877509","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.14877509","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Giovanni Bindi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giovanni Bindi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Philippe Esling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philippe Esling","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":0.44837457,"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":0.49970000982284546,"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":0.49970000982284546,"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":0.13680000603199005,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.12520000338554382,"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/leverage","display_name":"Leverage (statistics)","score":0.6209999918937683},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5196999907493591},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4957999885082245},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4819999933242798},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.460099995136261},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.44850000739097595},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4262000024318695},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.423799991607666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919999957084656},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6209999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5378999710083008},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4957999885082245},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4819999933242798},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.460099995136261},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4115999937057495},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877509","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877509","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.14877509","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877509","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"generative":[1,80],"models":[2],"are":[3],"able":[4,105],"to":[5,13,25,106,123,195],"generate":[6,26],"high-quality":[7,108],"artefacts":[8],"but":[9],"have":[10],"been":[11],"shown":[12],"struggle":[14],"with":[15,88,121,193],"compositional":[16,41,63],"reasoning,":[17],"which":[18],"can":[19,73],"be":[20],"defined":[21,66],"as":[22,173],"the":[23,38,49,77,93,151,178],"ability":[24],"complex":[27],"structures":[28],"from":[29],"simpler":[30],"elements.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,156],"focus":[36],"on":[37,138],"problem":[39],"of":[40,76,95,153,161,181],"representation":[42],"learning":[43,144],"for":[44],"music":[45],"data,":[46],"specifically":[47],"targeting":[48],"fully-unsupervised":[50],"setting.":[51],"We":[52,82],"propose":[53],"a":[54,68,158,189],"simple":[55],"and":[56,169],"extensible":[57],"framework":[58],"that":[59,72,84,101,113],"leverages":[60],"an":[61,145],"explicit":[62],"inductive":[64],"bias,":[65],"by":[67,143],"flexible":[69],"auto-encoding":[70],"objective":[71],"leverage":[74],"any":[75],"current":[78,134],"state-of-art":[79,135],"models.":[81],"demonstrate":[83],"our":[85,102,114,174],"framework,":[86],"used":[87],"diffusion":[89,148],"models,":[90],"naturally":[91],"addresses":[92],"task":[94],"unsupervised":[96,164],"audio":[97,184],"source":[98,126,165],"separation,":[99,166],"showing":[100],"model":[103,149],"is":[104],"perform":[107],"separation.":[109],"Our":[110],"findings":[111],"reveal":[112],"proposal":[115,175],"achieves":[116],"comparable":[117],"or":[118],"superior":[119],"performance":[120],"respect":[122,194],"other":[124,196],"blind":[125],"separation":[127],"methods":[128],"and,":[129],"furthermore,":[130],"it":[131,186],"even":[132],"surpasses":[133],"supervised":[136],"baselines":[137],"signal-to-interference":[139],"ratio":[140],"metrics.":[141],"Additionally,":[142],"a-posteriori":[146],"masking":[147],"in":[150,177],"space":[152,180],"composable":[154],"representations,":[155],"achieve":[157],"system":[159],"capable":[160],"seamlessly":[162],"performing":[163],"unconditional":[167],"generation,":[168],"variation":[170],"generation.":[171],"Finally,":[172],"works":[176],"latent":[179],"pre-trained":[182],"neural":[183,197],"codecs,":[185],"also":[187],"provides":[188],"lower":[190],"computational":[191],"cost":[192],"baselines.":[198]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}