{"id":"https://openalex.org/W4395065569","doi":"https://doi.org/10.1145/3638530.3654432","title":"LVNS-RAVE: Diversified audio generation with RAVE and Latent Vector Novelty Search","display_name":"LVNS-RAVE: Diversified audio generation with RAVE and Latent Vector Novelty Search","publication_year":2024,"publication_date":"2024-07-14","ids":{"openalex":"https://openalex.org/W4395065569","doi":"https://doi.org/10.1145/3638530.3654432"},"language":"en","primary_location":{"id":"doi:10.1145/3638530.3654432","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638530.3654432","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.14063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100313990","display_name":"Jinyue Guo","orcid":"https://orcid.org/0009-0003-7438-1483"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Jinyue Guo","raw_affiliation_strings":["Department of Musicology, University of Oslo, Oslo, Norway","RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0009-0003-7438-1483","affiliations":[{"raw_affiliation_string":"Department of Musicology, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037866774","display_name":"Anna-Maria Christodoulou","orcid":"https://orcid.org/0009-0003-7063-2062"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Anna-Maria Christodoulou","raw_affiliation_strings":["Department of Musicology, University of Oslo, Oslo, Norway","RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0009-0003-7063-2062","affiliations":[{"raw_affiliation_string":"Department of Musicology, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095848621","display_name":"Balint Laczko","orcid":"https://orcid.org/0009-0001-8337-2509"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Balint Laczko","raw_affiliation_strings":["Department of Musicology, University of Oslo, Oslo, Norway","RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0009-0001-8337-2509","affiliations":[{"raw_affiliation_string":"Department of Musicology, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051938848","display_name":"Kyrre Glette","orcid":"https://orcid.org/0000-0003-3550-3225"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Kyrre Glette","raw_affiliation_strings":["Department of Informatics, University of Oslo, Oslo, Norway","RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0003-3550-3225","affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]},{"raw_affiliation_string":"RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184942183"],"apc_list":null,"apc_paid":null,"fwci":0.0895,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"667","last_page":"670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9934999942779541,"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/novelty","display_name":"Novelty","score":0.7209382653236389},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6612201929092407},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4868980944156647},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0767928957939148}],"concepts":[{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.7209382653236389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6612201929092407},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4868980944156647},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0767928957939148},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3638530.3654432","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3638530.3654432","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.14063","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.14063","pdf_url":"https://arxiv.org/pdf/2404.14063","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.14063","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.14063","pdf_url":"https://arxiv.org/pdf/2404.14063","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6000000238418579,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7311193691","display_name":null,"funder_award_id":"262762","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"}],"funders":[{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395065569.pdf","grobid_xml":"https://content.openalex.org/works/W4395065569.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W78348860","https://openalex.org/W1584951677","https://openalex.org/W2008533620","https://openalex.org/W2099746672","https://openalex.org/W2151083897","https://openalex.org/W2519091744","https://openalex.org/W2593116425","https://openalex.org/W2897177022","https://openalex.org/W3154666256","https://openalex.org/W3177065897","https://openalex.org/W3206122975","https://openalex.org/W4309117899","https://openalex.org/W4318718630"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381242807","https://openalex.org/W3126131230","https://openalex.org/W2347541121","https://openalex.org/W2080951048","https://openalex.org/W4288804799","https://openalex.org/W3032237421","https://openalex.org/W2390346111"],"abstract_inverted_index":{"Evolutionary":[0,22,58],"Algorithms":[1,23,59],"and":[2,31,45,60,67,79,143],"Generative":[3,36,61],"Deep":[4,37,62],"Learning":[5,38,63],"have":[6,20],"been":[7],"two":[8],"of":[9,120],"the":[10,43,72,76,80,88,100,121,129],"most":[11],"powerful":[12],"tools":[13],"for":[14,140],"sound":[15,34,77,141],"generation":[16,122],"tasks.":[17],"However,":[18],"they":[19],"limitations:":[21],"require":[24],"complicated":[25],"designs,":[26],"posing":[27],"challenges":[28],"in":[29,87],"control":[30],"achieving":[32],"realistic":[33,66],"generation.":[35],"models":[39],"often":[40],"copy":[41],"from":[42],"dataset":[44],"lack":[46],"creativity.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"LVNS-RAVE,":[53],"a":[54,84,137],"method":[55,101],"to":[56,64],"combine":[57],"produce":[65],"novel":[68,106],"sounds.":[69],"We":[70],"use":[71],"RAVE":[73,116],"model":[74,82],"as":[75,83],"generator":[78],"VGGish":[81],"novelty":[85],"evaluator":[86],"Latent":[89],"Vector":[90],"Novelty":[91],"Search":[92],"(LVNS)":[93],"algorithm.":[94],"The":[95,118,132],"reported":[96],"experiments":[97],"show":[98],"that":[99],"can":[102,124,135],"successfully":[103],"generate":[104],"diversified,":[105],"audio":[107],"samples":[108],"under":[109],"different":[110,114],"mutation":[111,130],"setups":[112],"using":[113],"pre-trained":[115],"models.":[117],"characteristics":[119],"process":[123],"be":[125,136],"easily":[126],"controlled":[127],"with":[128],"parameters.":[131],"proposed":[133],"algorithm":[134],"creative":[138],"tool":[139],"artists":[142],"musicians.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2024-04-24T00:00:00"}