{"id":"https://openalex.org/W6967597117","doi":"https://doi.org/10.5281/zenodo.10265255","title":"White Box Search Over Audio Synthesizer Parameters","display_name":"White Box Search Over Audio Synthesizer Parameters","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6967597117","doi":"https://doi.org/10.5281/zenodo.10265255"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265255","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265255","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.10265255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuting Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuting Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zeyu Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Connelly Barnes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Connelly Barnes","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Adam Finkelstein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Finkelstein","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":0.31309731,"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":0.33320000767707825,"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":0.33320000767707825,"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":0.3255000114440918,"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":0.05620000138878822,"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/rendering","display_name":"Rendering (computer graphics)","score":0.4968000054359436},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.45019999146461487},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3984000086784363},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3944000005722046},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.38920000195503235},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.3779999911785126},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.3379000127315521},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.33649998903274536},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.32910001277923584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609000205993652},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39890000224113464},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.362199991941452},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.32910001277923584},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.3208000063896179},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C15627037","wikidata":"https://www.wikidata.org/wiki/Q541961","display_name":"Classification of discontinuities","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C534633266","wikidata":"https://www.wikidata.org/wiki/Q4774317","display_name":"Anti-aliasing","level":5,"score":0.2745000123977661},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265255","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265255","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.10265255","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265255","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":{"Synthesizer":[0],"parameter":[1,85],"inference":[2,86],"searches":[3],"for":[4,113],"a":[5,18,47,54,122,139,154],"set":[6],"of":[7,156],"patch":[8],"connections":[9],"and":[10,72,93,107,126,146,167],"parameters":[11,52,130,151],"to":[12,28,95,116,152],"generate":[13],"audio":[14,33,158],"that":[15,60],"best":[16],"matches":[17],"given":[19],"target":[20,157],"sound.":[21],"Such":[22],"optimization":[23],"tasks":[24],"benefit":[25],"from":[26],"access":[27],"accurate":[29],"gradients.":[30],"However,":[31],"typical":[32],"synths":[34],"incorporate":[35],"components":[36],"with":[37,143],"discontinuities":[38],"\u2013":[39,59],"such":[40,57,81,97],"as":[41,98,121],"sawtooth":[42],"or":[43,46,101],"square":[44],"waveforms,":[45],"categorical":[48],"search":[49,100],"over":[50],"discrete":[51],"like":[53,70],"choice":[55],"among":[56],"waveforms":[58],"thwart":[61],"conventional":[62],"automatic":[63],"differentiation":[64],"(AD).":[65],"AD":[66],"libraries":[67],"in":[68,164],"frameworks":[69],"TensorFlow":[71],"PyTorch":[73],"typically":[74],"ignore":[75],"discontinuities,":[76],"providing":[77],"incorrect":[78],"gradients":[79],"at":[80],"locations.":[82],"Thus,":[83],"SOTA":[84],"methods":[87,112],"avoid":[88],"differentiating":[89],"the":[90,119],"synth":[91,120,142],"directly,":[92],"resort":[94],"workarounds":[96],"genetic":[99],"neural":[102],"proxies.":[103],"Instead,":[104],"we":[105],"adapt":[106],"extend":[108],"recent":[109],"computer":[110],"graphics":[111],"differentiable":[114],"rendering":[115],"directly":[117],"differentiate":[118],"white":[123],"box":[124],"program,":[125],"thereby":[127],"optimize":[128],"its":[129,150],"using":[131,138],"gradient":[132],"descent.":[133],"We":[134],"evaluate":[135],"our":[136],"framework":[137],"generic":[140],"FM":[141],"ADSR,":[144],"noise,":[145],"IIR":[147],"filters,":[148],"adapting":[149],"match":[153],"variety":[155],"clips.":[159],"Our":[160],"method":[161],"outperforms":[162],"baselines":[163],"both":[165],"quantitative":[166],"qualitative":[168],"evaluations.":[169]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}