{"id":"https://openalex.org/W6949370363","doi":"https://doi.org/10.5281/zenodo.14877289","title":"Music2Latent: Consistency Autoencoders for Latent Audio Compression","display_name":"Music2Latent: Consistency Autoencoders for Latent Audio Compression","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6949370363","doi":"https://doi.org/10.5281/zenodo.14877289"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877289","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877289","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":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877289","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Marco Pasini","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Marco Pasini","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Stefan Lattner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Lattner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"George Fazekas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Fazekas","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":0.55251792,"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/T12979","display_name":"Cardiovascular Disease and Adiposity","score":0.1656000018119812,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12979","display_name":"Cardiovascular Disease and Adiposity","score":0.1656000018119812,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12291","display_name":"Pericarditis and Cardiac Tamponade","score":0.10580000281333923,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13381","display_name":"Heart rate and cardiovascular health","score":0.06669999659061432,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8587999939918518},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6298999786376953},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4941999912261963},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4537999927997589},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4424000084400177},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4424000084400177},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4032999873161316},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.37310001254081726},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36899998784065247}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8587999939918518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437999844551086},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6298999786376953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5806000232696533},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5241000056266785},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4537999927997589},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32409998774528503},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2615000009536743},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877289","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877289","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":"doi:10.5281/zenodo.14877289","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877289","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":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"audio":[1,13,24,44,122],"representations":[2],"in":[3,63,124],"a":[4,58,64],"compressed":[5,59],"continuous":[6,60,121],"latent":[7,61,140],"space":[8,62],"are":[9],"critical":[10],"for":[11],"generative":[12],"modeling":[14],"and":[15,99,127],"Music":[16],"Information":[17],"Retrieval":[18],"(MIR)":[19],"tasks.":[20],"However,":[21],"some":[22],"existing":[23,120],"autoencoders":[25,123],"have":[26],"limitations,":[27],"such":[28],"as":[29],"multi-stage":[30],"training":[31,67,152],"procedures,":[32],"slow":[33],"iterative":[34],"sampling,":[35],"or":[36],"low":[37],"reconstruction":[38,128],"quality.":[39],"We":[40,115],"introduce":[41],"Music2Latent,":[42],"an":[43,153],"autoencoder":[45,156],"that":[46,117],"overcomes":[47],"these":[48],"limitations":[49],"by":[50],"leveraging":[51],"consistency":[52,79,155],"models.":[53],"Music2Latent":[54,118],"encodes":[55],"samples":[56],"into":[57],"single":[65],"end-to-end":[66,154],"process":[68],"while":[69,130],"enabling":[70],"high-fidelity":[71],"single-step":[72],"reconstruction.":[73],"Key":[74],"innovations":[75],"include":[76],"conditioning":[77],"the":[78,147],"model":[80],"on":[81,134],"upsampled":[82],"encoder":[83],"outputs":[84],"at":[85,111,151],"all":[86],"levels":[87],"through":[88],"cross":[89],"connections,":[90],"using":[91,138],"frequency-wise":[92,101],"self-attention":[93],"to":[94,104],"capture":[95],"long-range":[96],"frequency":[97],"dependencies,":[98],"employing":[100],"learned":[102],"scaling":[103],"handle":[105],"varying":[106],"value":[107],"distributions":[108],"across":[109],"frequencies":[110],"different":[112],"noise":[113],"levels.":[114],"demonstrate":[116],"outperforms":[119],"sound":[125],"quality":[126],"accuracy":[129],"achieving":[131],"competitive":[132],"performance":[133],"downstream":[135],"MIR":[136],"tasks":[137],"its":[139],"representations.":[141],"To":[142],"our":[143],"knowledge,":[144],"this":[145],"represents":[146],"first":[148],"successful":[149],"attempt":[150],"model.":[157]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}