{"id":"https://openalex.org/W2736699890","doi":"https://doi.org/10.1109/ssci.2017.8280895","title":"GLSR-VAE: Geodesic latent space regularization for variational autoencoder architectures","display_name":"GLSR-VAE: Geodesic latent space regularization for variational autoencoder architectures","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2736699890","doi":"https://doi.org/10.1109/ssci.2017.8280895","mag":"2736699890"},"language":"en","primary_location":{"id":"doi:10.1109/ssci.2017.8280895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8280895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1707.04588","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051522702","display_name":"Ga\u00ebtan Hadjeres","orcid":"https://orcid.org/0000-0003-1462-6103"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["FR","JP"],"is_corresponding":false,"raw_author_name":"Gaetan Hadjeres","raw_affiliation_strings":["LIP6, Universit\u00e9 Pierre et Marie Curie, Paris","Sony CSL, Paris","LIP6, Universit\u00e9 Pierre et Marie Curie, Paris, Sony CSL, Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIP6, Universit\u00e9 Pierre et Marie Curie, Paris","institution_ids":["https://openalex.org/I39804081"]},{"raw_affiliation_string":"Sony CSL, Paris","institution_ids":["https://openalex.org/I4210122684"]},{"raw_affiliation_string":"LIP6, Universit\u00e9 Pierre et Marie Curie, Paris, Sony CSL, Paris","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061293973","display_name":"Frank Nielsen","orcid":"https://orcid.org/0000-0001-5728-0726"},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["FR","JP"],"is_corresponding":false,"raw_author_name":"Frank Nielsen","raw_affiliation_strings":["Ecole Polytechnique, France","Sony CSL, Tokyo","\u00c9cole Polytechnique, Palaiseau, France, Sony CSL, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique, France","institution_ids":["https://openalex.org/I142476485"]},{"raw_affiliation_string":"Sony CSL, Tokyo","institution_ids":["https://openalex.org/I4210122684"]},{"raw_affiliation_string":"\u00c9cole Polytechnique, Palaiseau, France, Sony CSL, Tokyo","institution_ids":["https://openalex.org/I142476485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111498117","display_name":"Fran\u00e7ois Pachet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Francois Pachet","raw_affiliation_strings":["Sony CSL, Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony CSL, Paris","institution_ids":["https://openalex.org/I4210122684"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.913,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.750901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9968000054359436,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9965000152587891,"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/autoencoder","display_name":"Autoencoder","score":0.8848271369934082},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7216351628303528},{"id":"https://openalex.org/keywords/geodesic","display_name":"Geodesic","score":0.6468245387077332},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6415642499923706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6305553913116455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5236794352531433},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.48476022481918335},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4244462251663208},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41792812943458557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34107887744903564},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.31444597244262695},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27971380949020386}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8848271369934082},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7216351628303528},{"id":"https://openalex.org/C165818556","wikidata":"https://www.wikidata.org/wiki/Q213488","display_name":"Geodesic","level":2,"score":0.6468245387077332},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6415642499923706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6305553913116455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5236794352531433},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.48476022481918335},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4244462251663208},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41792812943458557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34107887744903564},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31444597244262695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27971380949020386},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ssci.2017.8280895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2017.8280895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1707.04588","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.04588","pdf_url":"https://arxiv.org/pdf/1707.04588","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2736699890","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1707.04588","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1707.04588","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1707.04588","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1707.04588","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.04588","pdf_url":"https://arxiv.org/pdf/1707.04588","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2072128103","https://openalex.org/W2099111195","https://openalex.org/W2118776487","https://openalex.org/W2129192849","https://openalex.org/W2145094598","https://openalex.org/W2188365844","https://openalex.org/W2202109488","https://openalex.org/W2210838531","https://openalex.org/W2269752429","https://openalex.org/W2326533993","https://openalex.org/W2396566817","https://openalex.org/W2409027918","https://openalex.org/W2485135680","https://openalex.org/W2514141612","https://openalex.org/W2551906536","https://openalex.org/W2557283755","https://openalex.org/W2950067852","https://openalex.org/W2953046278","https://openalex.org/W4229633200","https://openalex.org/W4231109964","https://openalex.org/W6679224591","https://openalex.org/W6681096077","https://openalex.org/W6687045409","https://openalex.org/W6712395597","https://openalex.org/W6730558285"],"related_works":["https://openalex.org/W3035824977","https://openalex.org/W2959255678","https://openalex.org/W3021132617","https://openalex.org/W3170643636","https://openalex.org/W3201047144","https://openalex.org/W3047495882","https://openalex.org/W3128090829","https://openalex.org/W3088661541","https://openalex.org/W3034912393","https://openalex.org/W2772211716","https://openalex.org/W2968689209","https://openalex.org/W3090794770","https://openalex.org/W2804013387","https://openalex.org/W3126624604","https://openalex.org/W3093582368","https://openalex.org/W2990339437","https://openalex.org/W3006034899","https://openalex.org/W3183193032","https://openalex.org/W3042544668","https://openalex.org/W3206018546"],"abstract_inverted_index":{"VAEs":[0],"(Variational":[1],"AutoEncoders)":[2],"have":[3,15],"proved":[4],"to":[5,40,115,140],"be":[6],"powerful":[7],"in":[8,18,49,90,123,146],"the":[9,29,59,72,75,78,83,91,98,101,107,113,117,120],"context":[10],"of":[11,21,74,97,100,106,119,143],"density":[12],"modeling":[13],"and":[14,63,149],"been":[16],"used":[17],"a":[19,53,68,124,132],"variety":[20],"contexts":[22],"for":[23,58],"creative":[24],"purposes.":[25],"In":[26],"many":[27],"settings,":[28],"data":[30,76,122],"we":[31,37,138],"model":[32],"possesses":[33],"continuous":[34,125],"attributes":[35,99,118],"that":[36],"would":[38],"like":[39],"take":[41],"into":[42,77],"account":[43],"at":[44],"generation":[45,135],"time.":[46],"We":[47,127],"propose":[48],"this":[50,87],"paper":[51],"GLSR-VAE,":[52],"Geodesic":[54],"Latent":[55],"Space":[56],"Regularization":[57],"Variational":[60],"AutoEncoder":[61],"architecture":[62],"its":[64,129],"generalizations":[65],"which":[66],"allows":[67],"fine":[69],"control":[70],"on":[71,131],"embedding":[73],"latent":[79,93,109],"space.":[80],"When":[81],"augmenting":[82],"VAE":[84,108],"loss":[85],"with":[86],"regularization,":[88],"changes":[89,96],"learned":[92],"space":[94,110],"reflects":[95],"data.":[102],"This":[103],"deeper":[104],"understanding":[105],"structure":[111],"offers":[112],"possibility":[114],"modulate":[116],"generated":[121],"way.":[126,151],"demonstrate":[128],"efficiency":[130],"monophonic":[133],"music":[134],"task":[136],"where":[137],"manage":[139],"generate":[141],"variations":[142],"discrete":[144],"sequences":[145],"an":[147],"intended":[148],"playful":[150]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2022-10-06T00:00:00"}