{"id":"https://openalex.org/W3215457199","doi":"https://doi.org/10.1109/icassp43922.2022.9746940","title":"Differentiable Wavetable Synthesis","display_name":"Differentiable Wavetable Synthesis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3215457199","doi":"https://doi.org/10.1109/icassp43922.2022.9746940","mag":"3215457199"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746940","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5017611842","display_name":"Siyuan Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyuan Shan","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068785610","display_name":"Lamtharn Hantrakul","orcid":"https://orcid.org/0000-0001-6697-8149"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lamtharn Hantrakul","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI) Team, ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI) Team, ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046063537","display_name":"Jitong Chen","orcid":"https://orcid.org/0000-0001-6084-043X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jitong Chen","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI) Team, ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI) Team, ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089615767","display_name":"Matt Avent","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matt Avent","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI) Team, ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI) Team, ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088487161","display_name":"David Trevelyan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Trevelyan","raw_affiliation_strings":["Speech, Audio & Music Intelligence (SAMI) Team, ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio & Music Intelligence (SAMI) Team, ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4598","last_page":"4602"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.998199999332428,"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/high-fidelity","display_name":"High fidelity","score":0.8231545686721802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7963606715202332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5791347622871399},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5743390321731567},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.573324978351593},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.548588216304779},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5402912497520447},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4888693690299988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37627077102661133},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.25551342964172363},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07452630996704102},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06102198362350464},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05456060171127319}],"concepts":[{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.8231545686721802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7963606715202332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5791347622871399},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5743390321731567},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.573324978351593},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.548588216304779},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5402912497520447},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4888693690299988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37627077102661133},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.25551342964172363},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07452630996704102},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06102198362350464},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05456060171127319},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746940","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W645380233","https://openalex.org/W1507269217","https://openalex.org/W1545063197","https://openalex.org/W1560393114","https://openalex.org/W2148228080","https://openalex.org/W2153579005","https://openalex.org/W2191779130","https://openalex.org/W2259990426","https://openalex.org/W2519091744","https://openalex.org/W2530887700","https://openalex.org/W2604184139","https://openalex.org/W2606176153","https://openalex.org/W2759171953","https://openalex.org/W2910577860","https://openalex.org/W2950527759","https://openalex.org/W2962866891","https://openalex.org/W2962981281","https://openalex.org/W2964307104","https://openalex.org/W2989708046","https://openalex.org/W2995233853","https://openalex.org/W3000389243","https://openalex.org/W3033411150","https://openalex.org/W3095617022","https://openalex.org/W3101943858","https://openalex.org/W3130016944","https://openalex.org/W3138918949","https://openalex.org/W3138953166","https://openalex.org/W3162289111","https://openalex.org/W3165004824","https://openalex.org/W4294170691","https://openalex.org/W4298374011","https://openalex.org/W4298580827","https://openalex.org/W4303633609","https://openalex.org/W6682691769","https://openalex.org/W6684821475","https://openalex.org/W6692743877","https://openalex.org/W6736356763","https://openalex.org/W6736723571","https://openalex.org/W6748409065","https://openalex.org/W6758675244","https://openalex.org/W6770046961","https://openalex.org/W6771763809","https://openalex.org/W6778823374","https://openalex.org/W6780252696","https://openalex.org/W6784488536","https://openalex.org/W6791662060","https://openalex.org/W6792340124","https://openalex.org/W6795972600"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4293777179","https://openalex.org/W4385452045","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W2332512904","https://openalex.org/W4224231624","https://openalex.org/W2319626700"],"abstract_inverted_index":{"Differentiable":[0],"Wavetable":[1],"Synthesis":[2],"(DWTS)":[3],"is":[4],"a":[5,13,39,66],"technique":[6],"for":[7,81],"neural":[8],"audio":[9,26,52,57,85],"synthesis":[10,27],"which":[11],"learns":[12],"dictionary":[14,41],"of":[15,42,69],"one-period":[16],"waveforms":[17,43],"i.e.":[18],"wavetables,":[19],"through":[20],"end-to-end":[21],"training.":[22],"We":[23],"achieve":[24],"high-fidelity":[25],"with":[28],"as":[29,31,60],"little":[30],"10":[32],"to":[33],"20":[34],"wavetables":[35,80],"and":[36,83],"demonstrate":[37],"how":[38],"data-driven":[40],"opens":[44],"up":[45],"unprecedented":[46],"one-shot":[47],"learning":[48],"paradigms":[49],"on":[50],"short":[51],"clips.":[53],"Notably,":[54],"we":[55,73],"show":[56],"manipulations,":[58],"such":[59],"high":[61],"quality":[62],"pitch-shifting,":[63],"using":[64,78],"only":[65],"few":[67],"seconds":[68],"input":[70],"audio.":[71],"Lastly,":[72],"investigate":[74],"performance":[75],"gains":[76],"from":[77],"learned":[79],"realtime":[82],"interactive":[84],"synthesis.":[86]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}