{"id":"https://openalex.org/W6967482322","doi":"https://doi.org/10.5281/zenodo.10265299","title":"VampNet: Music Generation via Masked Acoustic Token Modeling","display_name":"VampNet: Music Generation via Masked Acoustic Token Modeling","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6967482322","doi":"https://doi.org/10.5281/zenodo.10265299"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265299","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265299","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.10265299","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hugo Flores Garc\u00eda","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hugo Flores Garc\u00eda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Prem Seetharaman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prem Seetharaman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Rithesh Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rithesh Kumar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Bryan Pardo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Pardo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.31243124,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.7333999872207642,"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":0.7333999872207642,"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":0.13670000433921814,"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":0.031599998474121094,"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/security-token","display_name":"Security token","score":0.7157999873161316},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5099999904632568},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47119998931884766},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.44209998846054077},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4316999912261963},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3684999942779541},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.34200000762939453},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.32760000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7439000010490417},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7157999873161316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.660099983215332},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47119998931884766},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32760000228881836},{"id":"https://openalex.org/C77801330","wikidata":"https://www.wikidata.org/wiki/Q1363413","display_name":"Auditory masking","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29660001397132874},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C178884764","wikidata":"https://www.wikidata.org/wiki/Q510293","display_name":"Musical acoustics","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265299","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265299","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.10265299","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265299","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4245792329311371}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,16,74],"introduce":[1],"VampNet,":[2],"a":[3,18,36,49,59,123],"masked":[4],"acoustic":[5],"token":[6],"modeling":[7],"approach":[8],"to":[9,27,55,87],"music":[10,30,90,125],"synthesis,":[11],"compression,":[12,91],"inpainting,":[13,92],"and":[14,95,110,129],"variation.":[15],"use":[17],"variable":[19],"masking":[20,39],"schedule":[21],"during":[22,43],"training":[23],"which":[24],"allows":[25],"us":[26],"sample":[28],"coherent":[29,70],"from":[31],"the":[32,115],"model":[33],"by":[34,77],"applying":[35],"variety":[37],"of":[38,105,114],"approaches":[40],"(called":[41],"prompts)":[42],"inference.":[44],"VampNet":[45,67,79,102,122],"is":[46,103],"non-autoregressive,":[47],"leveraging":[48],"bidirectional":[50],"transformer":[51],"architecture":[52],"that":[53,76],"attends":[54],"all":[56],"tokens":[57],"in":[58,80],"forward":[60],"pass.":[61],"With":[62],"just":[63],"36":[64],"sampling":[65],"passes,":[66],"can":[68,84],"generate":[69],"high-fidelity":[71],"musical":[72],"waveforms.":[73],"show":[75],"prompting":[78,119],"various":[81],"ways,":[82],"we":[83],"apply":[85],"it":[86],"tasks":[88],"like":[89],"outpainting,":[93],"continuation,":[94],"looping":[96],"with":[97],"variation":[98],"(vamping).":[99],"Appropriately":[100],"prompted,":[101],"capable":[104],"maintaining":[106],"style,":[107],"genre,":[108],"instrumentation,":[109],"other":[111],"high-level":[112],"aspects":[113],"music.":[116],"This":[117],"flexible":[118],"capability":[120],"makes":[121],"powerful":[124],"co-creation":[126],"tool.":[127],"Code":[128],"audio":[130],"samples":[131],"are":[132],"available":[133],"online.":[134]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}