{"id":"https://openalex.org/W4391948635","doi":"https://doi.org/10.1109/taslp.2024.3364616","title":"NoiseBandNet: Controllable Time-Varying Neural Synthesis of Sound Effects Using Filterbanks","display_name":"NoiseBandNet: Controllable Time-Varying Neural Synthesis of Sound Effects Using Filterbanks","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391948635","doi":"https://doi.org/10.1109/taslp.2024.3364616"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3364616","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3364616","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2024.3364616","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046636116","display_name":"Adri\u00e1n Barahona-R\u00edos","orcid":"https://orcid.org/0000-0001-7538-2793"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adri\u00e1n Barahona-R\u00edos","raw_affiliation_strings":["Department of Computer Science, University of York, York, U.K"],"raw_orcid":"https://orcid.org/0000-0001-7538-2793","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of York, York, U.K","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071036967","display_name":"Tom Collins","orcid":"https://orcid.org/0000-0001-7880-5093"},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Collins","raw_affiliation_strings":["Frost School of Music, University of Miami, Coral Gables, FL, USA"],"raw_orcid":"https://orcid.org/0000-0001-7880-5093","affiliations":[{"raw_affiliation_string":"Frost School of Music, University of Miami, Coral Gables, FL, USA","institution_ids":["https://openalex.org/I145608581"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8446,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6791053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"1573","last_page":"1585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9988999962806702,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4682632088661194},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.41242730617523193},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4105370044708252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3922288417816162},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3224259614944458},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09587410092353821}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4682632088661194},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.41242730617523193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4105370044708252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3922288417816162},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3224259614944458},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09587410092353821}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3364616","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3364616","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2024.3364616","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3364616","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2033875152","https://openalex.org/W2062663442","https://openalex.org/W2088432713","https://openalex.org/W2105482032","https://openalex.org/W2116479175","https://openalex.org/W2143637834","https://openalex.org/W2166140710","https://openalex.org/W2748617861","https://openalex.org/W2792764867","https://openalex.org/W2888185520","https://openalex.org/W2972478942","https://openalex.org/W2998588915","https://openalex.org/W3015205011","https://openalex.org/W3015338123","https://openalex.org/W3084577344","https://openalex.org/W3097935827","https://openalex.org/W3127705815","https://openalex.org/W3207785894","https://openalex.org/W3214281017","https://openalex.org/W3215457199","https://openalex.org/W4226409935","https://openalex.org/W4238247913","https://openalex.org/W4254033587","https://openalex.org/W4306679376","https://openalex.org/W4307323391","https://openalex.org/W4309117899","https://openalex.org/W4372260533","https://openalex.org/W4372263438","https://openalex.org/W4372348434","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6749825310","https://openalex.org/W6751667549","https://openalex.org/W6771763809","https://openalex.org/W6782701656","https://openalex.org/W6782757012","https://openalex.org/W6787485125","https://openalex.org/W6791662060","https://openalex.org/W6797004501","https://openalex.org/W6798451072","https://openalex.org/W6803922201","https://openalex.org/W6838697816","https://openalex.org/W6840348479","https://openalex.org/W6841323064","https://openalex.org/W6842676699","https://openalex.org/W6845479124","https://openalex.org/W6846529734","https://openalex.org/W6849109464","https://openalex.org/W6850898621","https://openalex.org/W6892528592"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027"],"abstract_inverted_index":{"Controllable":[0],"neural":[1],"audio":[2,102],"synthesis":[3],"of":[4,19,54,80,89,108,119,134,151],"sound":[5,58,98,132],"effects":[6,59,133],"is":[7],"a":[8,65,87,124],"challenging":[9],"task":[10],"due":[11],"to":[12,32,105],"the":[13,20,77,109],"potential":[14,148],"scarcity":[15],"and":[16,34,37,44,56,96,141,159],"spectro-temporal":[17],"variance":[18],"data.":[21],"Differentiable":[22],"digital":[23],"signal":[24],"processing":[25],"(DDSP)":[26],"synthesisers":[27],"have":[28],"been":[29],"successfully":[30],"employed":[31],"model":[33],"control":[35,165],"musical":[36],"harmonic":[38,78],"signals":[39],"using":[40],"relatively":[41],"limited":[42],"data":[43],"computational":[45],"resources.":[46],"Here":[47],"we":[48,145],"propose":[49],"NoiseBandNet,":[50,152],"an":[51],"architecture":[52],"capable":[53],"synthesising":[55],"controlling":[57],"by":[60,153,160],"filtering":[61],"white":[62],"noise":[63,111],"through":[64],"filterbank,":[66],"thus":[67],"going":[68],"further":[69],"than":[70],"previous":[71],"systems":[72],"that":[73],"make":[74],"assumptions":[75],"about":[76],"nature":[79],"sounds.":[81],"We":[82],"evaluate":[83],"our":[84],"approach":[85],"via":[86],"series":[88],"experiments,":[90],"modelling":[91],"footsteps,":[92],"thunderstorm,":[93],"pottery,":[94],"knocking,":[95],"metal":[97],"effects.":[99],"Comparing":[100],"NoiseBandNet":[101,113],"reconstruction":[103],"capabilities":[104],"four":[106],"variants":[107],"DDSP-filtered":[110],"synthesiser,":[112],"scores":[114],"higher":[115],"in":[116],"nine":[117],"out":[118],"ten":[120],"evaluation":[121],"categories,":[122],"establishing":[123],"flexible":[125],"DDSP":[126],"method":[127],"for":[128],"generating":[129,154],"time-varying,":[130],"inharmonic":[131],"arbitrary":[135],"length":[136],"with":[137],"both":[138],"good":[139],"time":[140],"frequency":[142],"resolution.":[143],"Finally,":[144],"introduce":[146],"some":[147],"creative":[149],"uses":[150],"variations,":[155],"performing":[156],"loudness":[157],"transfer,":[158],"training":[161],"it":[162],"on":[163],"user-defined":[164],"curves.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}