{"id":"https://openalex.org/W4416251020","doi":"https://doi.org/10.1109/waspaa66052.2025.11230953","title":"Can Large Language Models Predict Audio Effects Parameters from Natural Language?","display_name":"Can Large Language Models Predict Audio Effects Parameters from Natural Language?","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416251020","doi":"https://doi.org/10.1109/waspaa66052.2025.11230953"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230953","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/A5010952526","display_name":"SeungHeon Doh","orcid":"https://orcid.org/0000-0002-8448-9928"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seungheon Doh","raw_affiliation_strings":["KAIST,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031164776","display_name":"Junghyun Koo","orcid":"https://orcid.org/0009-0004-4468-0367"},"institutions":[{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junghyun Koo","raw_affiliation_strings":["Sony AI,Japan"],"affiliations":[{"raw_affiliation_string":"Sony AI,Japan","institution_ids":["https://openalex.org/I4210143797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017282176","display_name":"Marco A. Mart\u00ednez-Ram\u00edrez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marco A. Mart\u00ednez-Ram\u00edrez","raw_affiliation_strings":["Sony AI,Japan"],"affiliations":[{"raw_affiliation_string":"Sony AI,Japan","institution_ids":["https://openalex.org/I4210143797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103537853","display_name":"Wei\u2010Hsiang Liao","orcid":"https://orcid.org/0000-0003-4113-1894"},"institutions":[{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wei-Hsiang Liao","raw_affiliation_strings":["Sony AI,Japan"],"affiliations":[{"raw_affiliation_string":"Sony AI,Japan","institution_ids":["https://openalex.org/I4210143797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["KAIST,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony AI,Japan"],"affiliations":[{"raw_affiliation_string":"Sony AI,Japan","institution_ids":["https://openalex.org/I4210143797"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010952526"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37385499,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.3257000148296356,"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":0.3257000148296356,"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":0.2842999994754791,"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/T10863","display_name":"Voice and Speech Disorders","score":0.07119999825954437,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6561999917030334},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6510000228881836},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5641999840736389},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.49799999594688416},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45899999141693115},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.43479999899864197},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.38109999895095825},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.37959998846054077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386000156402588},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6561999917030334},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6510000228881836},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5641999840736389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5267999768257141},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49799999594688416},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.43479999899864197},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38999998569488525},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.38109999895095825},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.350600004196167},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.3391999900341034},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.33570000529289246},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C75755367","wikidata":"https://www.wikidata.org/wiki/Q104531076","display_name":"Equalization (audio)","level":3,"score":0.3244999945163727},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3131999969482422},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.30869999527931213},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230953","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":21,"referenced_works":["https://openalex.org/W2002507711","https://openalex.org/W2007659739","https://openalex.org/W2086286498","https://openalex.org/W2346272251","https://openalex.org/W2522241130","https://openalex.org/W2525342958","https://openalex.org/W2525411606","https://openalex.org/W2526050071","https://openalex.org/W3178031393","https://openalex.org/W4287509873","https://openalex.org/W4296598528","https://openalex.org/W4307977691","https://openalex.org/W4372260310","https://openalex.org/W4372263680","https://openalex.org/W4372266552","https://openalex.org/W4392908974","https://openalex.org/W4392909390","https://openalex.org/W4402670276","https://openalex.org/W4402727293","https://openalex.org/W4408354559","https://openalex.org/W4412888825"],"related_works":[],"abstract_inverted_index":{"In":[0],"music":[1,90,156],"production,":[2,147],"manipulating":[3],"audio":[4,87,102,146],"effects":[5,88],"(Fx)":[6],"parameters":[7,33,62,74],"through":[8],"natural":[9,55,131],"language":[10,56,132],"has":[11],"the":[12,47,59,81,149],"potential":[13],"to":[14,30,58,134],"reduce":[15],"technical":[16],"barriers":[17],"for":[18,63,145,151],"non-experts.":[19],"We":[20,67],"present":[21],"LLM2Fx,":[22],"a":[23,76],"framework":[24],"leveraging":[25],"Large":[26],"Language":[27],"Models":[28],"(LLMs)":[29],"predict":[31],"Fx":[32,61,73,119,136],"directly":[34],"from":[35],"textual":[36],"descriptions":[37,57,133],"without":[38],"requiring":[39],"task-specific":[40],"training":[41],"or":[42],"fine-tuning.":[43],"Our":[44,114],"approach":[45],"address":[46],"text-to-effect":[48],"parameter":[49,120],"prediction":[50],"(Text2Fx)":[51],"task":[52],"by":[53],"mapping":[54],"corresponding":[60],"equalization":[64],"and":[65,86,111,154],"reverberation.":[66],"demonstrate":[68,116],"that":[69,79,117],"LLMs":[70,139],"can":[71,140],"generate":[72],"in":[75,89,129],"zero-shot":[77],"manner":[78],"elucidates":[80],"relationship":[82],"between":[83],"timbre":[84],"semantics":[85],"production.":[91],"To":[92],"enhance":[93],"performance,":[94],"we":[95],"introduce":[96],"three":[97],"types":[98],"of":[99],"in-context":[100],"examples:":[101],"Digital":[103],"Signal":[104],"Processing":[105],"(DSP)":[106],"features,":[107],"DSP":[108],"function":[109],"code,":[110],"few-shot":[112],"examples.":[113],"results":[115],"LLM-based":[118],"generation":[121],"outperforms":[122],"previous":[123],"optimization":[124],"approaches,":[125],"offering":[126],"competitive":[127],"performance":[128],"translating":[130],"appropriate":[135],"settings.":[137],"Furthermore,":[138],"serve":[141],"as":[142],"text-driven":[143],"interfaces":[144],"paving":[148],"way":[150],"more":[152],"intuitive":[153],"accessible":[155],"production":[157],"tools.<sup":[158],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[159],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[160]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}