{"id":"https://openalex.org/W6967619515","doi":"https://doi.org/10.5281/zenodo.10265371","title":"Inversynth II: Sound Matching via Self-Supervised Synthesizer-Proxy and Inference-Time Finetuning","display_name":"Inversynth II: Sound Matching via Self-Supervised Synthesizer-Proxy and Inference-Time Finetuning","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6967619515","doi":"https://doi.org/10.5281/zenodo.10265371"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265371","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265371","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":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10265371","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Oren Barkan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oren Barkan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shlomi Shvartzman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shlomi Shvartzman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Noy Uzrad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noy Uzrad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Moshe Laufer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moshe Laufer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Almog Elharar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Almog Elharar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Noam Koenigstein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noam Koenigstein","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.33446579,"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/T11309","display_name":"Music and Audio Processing","score":0.366100013256073,"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":0.366100013256073,"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":0.21150000393390656,"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/T10860","display_name":"Speech and Audio Processing","score":0.17720000445842743,"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/novelty","display_name":"Novelty","score":0.609499990940094},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5694000124931335},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5587000250816345},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43549999594688416},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4307999908924103},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.35659998655319214},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.3529999852180481},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.349700003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7886999845504761},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.609499990940094},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5694000124931335},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5587000250816345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4553999900817871},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43549999594688416},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35659998655319214},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.32850000262260437},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3046000003814697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2599000036716461}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265371","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265371","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":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10265371","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265371","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":"ConferencePaper"},"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":{"Synthesizers":[0],"are":[1],"widely":[2],"used":[3],"electronic":[4],"musical":[5],"instruments.":[6],"Given":[7],"an":[8],"input":[9,67],"sound,":[10],"inferring":[11],"the":[12,31,53,66,83],"underlying":[13],"synthesizer's":[14],"parameters":[15],"to":[16,91],"reproduce":[17],"it":[18],"is":[19,38,102],"a":[20,56,75],"difficult":[21],"task":[22],"known":[23],"as":[24],"sound-matching.":[25],"In":[26],"this":[27],"work,":[28],"we":[29,73],"tackle":[30],"problem":[32],"of":[33,48,55],"automatic":[34],"sound":[35],"matching,":[36],"which":[37],"otherwise":[39],"performed":[40],"manually":[41],"by":[42,64],"professional":[43],"audio":[44,70],"experts.":[45],"The":[46],"novelty":[47],"our":[49],"work":[50],"stems":[51],"from":[52],"introduction":[54],"novel":[57,76],"differentiable":[58],"synthesizer-proxy":[59],"that":[60,80],"enables":[61],"gradient-based":[62],"optimization":[63],"comparing":[65],"and":[68],"reproduced":[69],"signals.":[71],"Additionally,":[72],"introduce":[74],"self-supervised":[77],"finetuning":[78],"mechanism":[79],"further":[81],"refines":[82],"prediction":[84],"at":[85],"inference":[86],"time.":[87],"Both":[88],"contributions":[89],"lead":[90],"state-of-the-art":[92],"results,":[93],"outperforming":[94],"previous":[95],"methods":[96],"across":[97],"various":[98],"metrics.":[99],"Our":[100],"code":[101],"available":[103],"at:":[104],"https://github.com/inversynth/InverSynth2.":[105]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}