{"id":"https://openalex.org/W4416250991","doi":"https://doi.org/10.1109/waspaa66052.2025.11230964","title":"SILA: Signal-to-Language Augmentation for Enhanced Control in Text-to-Audio Generation","display_name":"SILA: Signal-to-Language Augmentation for Enhanced Control in Text-to-Audio Generation","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250991","doi":"https://doi.org/10.1109/waspaa66052.2025.11230964"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230964","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/A5101999829","display_name":"Sonal Kumar","orcid":"https://orcid.org/0009-0006-5516-3060"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sonal Kumar","raw_affiliation_strings":["Adobe Research,San Frnacisco,CA,USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research,San Frnacisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023673004","display_name":"Prem Seetharaman","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prem Seetharaman","raw_affiliation_strings":["Adobe Research,San Frnacisco,CA,USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research,San Frnacisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037548450","display_name":"Justin Salamon","orcid":"https://orcid.org/0000-0001-6345-4593"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Salamon","raw_affiliation_strings":["Adobe Research,San Frnacisco,CA,USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research,San Frnacisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland,College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110542743","display_name":"Oriol Nieto","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oriol Nieto","raw_affiliation_strings":["Adobe Research,San Frnacisco,CA,USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research,San Frnacisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101999829"],"corresponding_institution_ids":["https://openalex.org/I1306409833"],"apc_list":null,"apc_paid":null,"fwci":2.2732,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90497289,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.26969999074935913,"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":0.26969999074935913,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.10570000112056732,"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/T12128","display_name":"AI in Service Interactions","score":0.04610000178217888,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/key","display_name":"Key (lock)","score":0.5144000053405762},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4724999964237213},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46540001034736633},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.435699999332428},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4253999888896942},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.3959999978542328},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3885999917984009},{"id":"https://openalex.org/keywords/sound-production","display_name":"Sound production","score":0.3815999925136566},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3781000077724457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6802999973297119},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4724999964237213},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4390000104904175},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.435699999332428},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.3959999978542328},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3885999917984009},{"id":"https://openalex.org/C2992428333","wikidata":"https://www.wikidata.org/wiki/Q11461","display_name":"Sound production","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C2780544925","wikidata":"https://www.wikidata.org/wiki/Q569874","display_name":"Surround sound","level":3,"score":0.31610000133514404},{"id":"https://openalex.org/C38956757","wikidata":"https://www.wikidata.org/wiki/Q716215","display_name":"Audio feedback","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C116822448","wikidata":"https://www.wikidata.org/wiki/Q1879301","display_name":"Noise control","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C499572226","wikidata":"https://www.wikidata.org/wiki/Q1937950","display_name":"Sound design","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230964","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2013020033","https://openalex.org/W2593116425","https://openalex.org/W2945761034","https://openalex.org/W2962866891","https://openalex.org/W2963609956","https://openalex.org/W3015371781","https://openalex.org/W4205689591","https://openalex.org/W4372260310","https://openalex.org/W4390872297","https://openalex.org/W4398226295","https://openalex.org/W4403780831","https://openalex.org/W4408345930","https://openalex.org/W4408352247"],"related_works":[],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,19,80,127,151],"text-to-audio":[3,128],"generation":[4,129],"has":[5],"seen":[6],"significant":[7],"advancements,":[8],"and":[9,52,60,92,104,114,125,139,144],"yet":[10,31],"the":[11,16,78,97,109,123,149],"ability":[12],"to":[13,34],"finely":[14],"control":[15,39,95],"acoustic":[17,42,116],"characteristics":[18,83],"generated":[20,98],"audio":[21,112,137,158],"remains":[22],"under-explored.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"introduce":[28],"a":[29,90],"novel":[30],"simple":[32],"approach":[33,101,119,153],"generate":[35],"sound":[36,58,82,140],"effects":[37],"with":[38,163],"over":[40,96],"key":[41],"parameters":[43,64],"such":[44],"as":[45],"loudness,":[46],"pitch,":[47],"reverb,":[48],"fade,":[49],"brightness,":[50],"noise":[51],"duration,":[53],"enabling":[54,89],"creative":[55,136],"applications":[56],"in":[57,87,154],"design":[59],"content":[61],"creation.":[62],"These":[63],"extend":[65],"beyond":[66],"traditional":[67],"Digital":[68],"Signal":[69],"Processing":[70],"(DSP)":[71],"techniques,":[72],"incorporating":[73],"learned":[74],"representations":[75],"that":[76,160],"capture":[77],"subtleties":[79],"how":[81],"can":[84],"be":[85],"shaped":[86],"context,":[88],"richer":[91],"more":[93],"nuanced":[94],"audio.":[99],"Our":[100,118,142],"is":[102,105],"model-agnostic":[103],"based":[106],"on":[107],"learning":[108],"disentanglement":[110],"between":[111],"semantics":[113],"its":[115],"features.":[117],"not":[120],"only":[121],"enhances":[122],"versatility":[124],"expressiveness":[126],"but":[130],"also":[131],"opens":[132],"new":[133],"avenues":[134],"for":[135],"production":[138],"design.":[141],"objective":[143],"subjective":[145],"evaluation":[146],"results":[147],"demonstrate":[148],"effectiveness":[150],"our":[152],"producing":[155],"high-quality,":[156],"customizable":[157],"outputs":[159],"align":[161],"closely":[162],"user":[164],"specifications.":[165],"Sound":[166],"examples":[167],"are":[168],"available":[169],"at:":[170],"https://sites.google.com/view/sila-waspaa/":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-11-14T00:00:00"}