{"id":"https://openalex.org/W7108717168","doi":"https://doi.org/10.5281/zenodo.17811388","title":"Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching","display_name":"Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108717168","doi":"https://doi.org/10.5281/zenodo.17811388"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811388","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811388","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.17811388","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ben Hayes","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ben Hayes","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Charalampos Saitis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charalampos Saitis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Gy\u00f6rgy Fazekas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gy\u00f6rgy 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":0.59937212,"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":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.3172999918460846,"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":0.3172999918460846,"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":0.299699991941452,"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":0.18619999289512634,"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/equivariant-map","display_name":"Equivariant map","score":0.6887000203132629},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5893999934196472},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.5020999908447266},{"id":"https://openalex.org/keywords/homogeneous-space","display_name":"Homogeneous space","score":0.49570000171661377},{"id":"https://openalex.org/keywords/conic-section","display_name":"Conic section","score":0.4887999892234802},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45489999651908875},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4244000017642975},{"id":"https://openalex.org/keywords/symmetry","display_name":"Symmetry (geometry)","score":0.38089999556541443},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.36419999599456787}],"concepts":[{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.6887000203132629},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5893999934196472},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.5020999908447266},{"id":"https://openalex.org/C96469262","wikidata":"https://www.wikidata.org/wiki/Q1324364","display_name":"Homogeneous space","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C108598597","wikidata":"https://www.wikidata.org/wiki/Q124255","display_name":"Conic section","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48730000853538513},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4787999987602234},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45489999651908875},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4244000017642975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40689998865127563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3822000026702881},{"id":"https://openalex.org/C2779886137","wikidata":"https://www.wikidata.org/wiki/Q21030012","display_name":"Symmetry (geometry)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C12455157","wikidata":"https://www.wikidata.org/wiki/Q7835331","display_name":"Transposition (logic)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.27489998936653137},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811388","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811388","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.17811388","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811388","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":{"Many":[0],"audio":[1,150,162],"synthesizers":[2],"can":[3],"produce":[4],"the":[5,13,35,92,95],"same":[6],"signal":[7],"given":[8],"different":[9],"parameter":[10,97],"configurations,":[11],"meaning":[12],"inversion":[14],"from":[15,133],"sound":[16],"to":[17,31,138],"parameters":[18],"is":[19,28,103],"an":[20],"inherently":[21],"ill-posed":[22],"problem.":[23],"We":[24],"show":[25,81],"that":[26,51,82,101,128],"this":[27],"largely":[29],"due":[30],"intrinsic":[32],"symmetries":[33,117,132],"of":[34,76,94],"synthesizer,":[36],"and":[37,158],"focus":[38],"in":[39,118,147],"particular":[40],"on":[41,47],"permutation":[42,56,109],"invariance.":[43],"First,":[44],"we":[45,80,99,121,152],"demonstrate":[46],"a":[48,63,77,83,108,124,141],"synthetic":[49],"task":[50],"regressing":[52],"point":[53],"estimates":[54],"under":[55],"symmetry":[57],"degrades":[58],"performance,":[59],"even":[60],"when":[61],"using":[62,107],"permutation-invariant":[64],"loss":[65],"function":[66],"or":[67],"symmetry-breaking":[68],"heuristics.":[69],"Then,":[70],"viewing":[71],"equivalent":[72],"solutions":[73],"as":[74],"modes":[75],"probability":[78],"distribution,":[79,98],"conditional":[84],"generative":[85,159],"model":[86],"substantially":[87],"improves":[88],"performance.":[89],"Further,":[90],"acknowledging":[91],"invariance":[93],"implicit":[96],"find":[100,153],"performance":[102],"further":[104],"improved":[105],"by":[106],"equivariant":[110],"continuous":[111],"normalizing":[112],"flow.":[113],"To":[114],"accommodate":[115],"intriciate":[116],"real":[119,148],"synthesizers,":[120],"also":[122],"propose":[123],"relaxed":[125],"equivariance":[126],"strategy":[127],"adaptively":[129],"discovers":[130],"relevant":[131],"data.":[134],"Applying":[135],"our":[136,154],"method":[137,155],"Surge":[139],"XT,":[140],"full-featured":[142],"open":[143],"source":[144],"synthesizer":[145],"used":[146],"world":[149],"production,":[151],"outperforms":[156],"regression":[157],"baselines":[160],"across":[161],"reconstruction":[163],"metrics.":[164]},"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}