{"id":"https://openalex.org/W4416250950","doi":"https://doi.org/10.1109/waspaa66052.2025.11230974","title":"Modulation Discovery with Differentiable Digital Signal Processing","display_name":"Modulation Discovery with Differentiable Digital Signal Processing","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250950","doi":"https://doi.org/10.1109/waspaa66052.2025.11230974"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082664845","display_name":"Christopher Mitcheltree","orcid":"https://orcid.org/0000-0002-2844-3650"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Christopher Mitcheltree","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072794436","display_name":"Hao Tan","orcid":"https://orcid.org/0000-0003-1153-2726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Hao Tan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111403298","display_name":"Joshua D. Reiss","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joshua D. Reiss","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082664845"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45326195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.638700008392334,"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":0.638700008392334,"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":0.14569999277591705,"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":0.04500000178813934,"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/interpretability","display_name":"Interpretability","score":0.8371000289916992},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.6283000111579895},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.515999972820282},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.48420000076293945},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.4706999957561493},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4625000059604645},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.4406999945640564},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4311999976634979},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.41130000352859497}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8371000289916992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6431000232696533},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.6283000111579895},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.515999972820282},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.4706999957561493},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.4625999927520752},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4625000059604645},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4311999976634979},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C52773712","wikidata":"https://www.wikidata.org/wiki/Q175022","display_name":"Digital signal","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38600000739097595},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.38100001215934753},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C158411068","wikidata":"https://www.wikidata.org/wiki/Q2720568","display_name":"Digital control","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C25915539","wikidata":"https://www.wikidata.org/wiki/Q220786","display_name":"Automatic frequency control","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.2515999972820282},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2103387126","https://openalex.org/W2345690065","https://openalex.org/W2791716806","https://openalex.org/W2972478942","https://openalex.org/W2998588915","https://openalex.org/W3015338123","https://openalex.org/W3159239022","https://openalex.org/W3215457199","https://openalex.org/W4285606794","https://openalex.org/W4316660651","https://openalex.org/W4390745914","https://openalex.org/W4405584712","https://openalex.org/W4412072230"],"related_works":[],"abstract_inverted_index":{"Modulations":[0],"are":[1,60],"a":[2,49,85,109,159],"critical":[3],"part":[4],"of":[5,14,78,115],"sound":[6,50],"design":[7],"and":[8,16,27,53,76,97,122,133,141,148,152],"music":[9],"production,":[10],"enabling":[11],"the":[12,37,43,73,79,105,113,135,154],"creation":[13],"complex":[15],"evolving":[17],"audio.":[18],"Modern":[19],"synthesizers":[20],"provide":[21,153],"envelopes,":[22],"low":[23],"frequency":[24],"oscillators":[25],"(LFOs),":[26],"more":[28],"parameter":[29,57,69],"automation":[30],"tools":[31],"that":[32,89],"allow":[33],"users":[34],"to":[35,47,103,128],"modulate":[36],"output":[38],"with":[39],"ease.":[40],"However,":[41],"determining":[42],"modulation":[44,81,91],"signals":[45],"used":[46],"create":[48],"is":[51],"difficult,":[52],"existing":[54],"sound-matching":[55,87],"/":[56],"estimation":[58],"systems":[59],"often":[61],"uninterpretable":[62],"black":[63],"boxes":[64],"or":[65],"predict":[66],"high-dimensional":[67],"framewise":[68],"values":[70],"without":[71],"considering":[72],"shape,":[74],"structure,":[75],"routing":[77],"underlying":[80],"curves.":[82],"We":[83,111,144],"propose":[84],"neural":[86],"approach":[88,117],"leverages":[90],"extraction,":[92],"constrained":[93],"control":[94],"signal":[95,100],"parameterizations,":[96],"differentiable":[98],"digital":[99],"processing":[101],"(DDSP)":[102],"discover":[104],"modulations":[106],"present":[107],"in":[108,158],"sound.":[110],"demonstrate":[112],"effectiveness":[114],"our":[116,146],"on":[118],"highly":[119],"modulated":[120],"synthetic":[121],"real":[123],"audio":[124,149],"samples,":[125],"its":[126],"applicability":[127],"different":[129],"DDSP":[130,156],"synth":[131],"architectures,":[132],"investigate":[134],"trade-off":[136],"it":[137],"incurs":[138],"between":[139],"interpretability":[140],"soundmatching":[142],"accuracy.":[143],"make":[145],"code":[147],"samples":[150],"available":[151],"trained":[155],"synths":[157],"VST":[160],"plugin.":[161]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}