{"id":"https://openalex.org/W4408354559","doi":"https://doi.org/10.1109/icassp49660.2025.10890334","title":"Text2FX: Harnessing CLAP Embeddings for Text-Guided Audio Effects","display_name":"Text2FX: Harnessing CLAP Embeddings for Text-Guided Audio Effects","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354559","doi":"https://doi.org/10.1109/icassp49660.2025.10890334"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5111843038","display_name":"A. K. Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Annie Chu","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075935325","display_name":"Patrick O\u2019Reilly","orcid":"https://orcid.org/0000-0002-6205-2354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick O\u2019Reilly","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Julia Barnett","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julia Barnett","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102878078","display_name":"Bryan Pardo","orcid":"https://orcid.org/0000-0002-1427-6492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Pardo","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0351,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96252223,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9958999752998352,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9908999800682068,"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/computer-science","display_name":"Computer science","score":0.7008765935897827},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42759302258491516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7008765935897827},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42759302258491516}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":25,"referenced_works":["https://openalex.org/W2086381917","https://openalex.org/W2522241130","https://openalex.org/W2525342958","https://openalex.org/W2525411606","https://openalex.org/W2593116425","https://openalex.org/W2965494588","https://openalex.org/W2972359262","https://openalex.org/W4225326921","https://openalex.org/W4287509873","https://openalex.org/W4307977691","https://openalex.org/W4312740349","https://openalex.org/W4372266552","https://openalex.org/W4386076215","https://openalex.org/W4390745914","https://openalex.org/W6629404720","https://openalex.org/W6697326221","https://openalex.org/W6757202746","https://openalex.org/W6766320909","https://openalex.org/W6771763809","https://openalex.org/W6784892142","https://openalex.org/W6791353385","https://openalex.org/W6868884132","https://openalex.org/W6871004077","https://openalex.org/W6874673833","https://openalex.org/W6911776542"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"work":[1],"introduces":[2],"Text2FX,":[3],"a":[4,54,125],"method":[5],"that":[6,70],"leverages":[7],"CLAP":[8,71,85],"embeddings":[9],"and":[10,22,34,64,79,114,132,139,148],"differentiable":[11,117],"digital":[12],"signal":[13],"processing":[14],"to":[15,58,86,89,102,135],"control":[16],"audio":[17,77,90,118,134],"effects,":[18],"such":[19],"as":[20],"equalization":[21,113],"reverberation,":[23,115],"using":[24,84],"open-vocabulary":[25,59],"natural":[26],"language":[27],"prompts":[28,131],"(e.g.,":[29],"\"make":[30],"this":[31,98],"sound":[32,60],"in-your-face":[33],"bold\").":[35],"Text2FX":[36],"operates":[37],"without":[38],"retraining":[39],"any":[40,103,116],"models,":[41],"relying":[42],"instead":[43],"on":[44],"single-instance":[45],"optimization":[46,82],"within":[47],"the":[48,137],"existing":[49],"embedding":[50,106],"space,":[51],"thus":[52],"enabling":[53],"flexible,":[55],"scalable":[56],"approach":[57,99],"transformations":[61],"through":[62],"interpretable":[63],"disentangled":[65],"FX":[66],"manipulation.":[67],"We":[68,123],"show":[69],"encodes":[72],"valuable":[73],"information":[74],"for":[75],"controlling":[76],"effects":[78],"propose":[80],"two":[81],"approaches":[83],"map":[87],"text":[88,130],"effect":[91,119],"parameters.":[92],"While":[93],"we":[94,110],"demonstrate":[95,111],"with":[96,112,128,144],"CLAP,":[97],"is":[100],"applicable":[101],"shared":[104],"text-audio":[105],"space.":[107],"Similarly,":[108],"while":[109],"may":[120],"be":[121],"controlled.":[122],"conduct":[124],"listener":[126],"study":[127],"diverse":[129],"source":[133],"evaluate":[136],"quality":[138],"alignment":[140],"of":[141],"these":[142],"methods":[143],"human":[145],"perception.":[146],"Demos":[147],"code":[149],"are":[150],"available":[151],"at":[152],"anniejchu.github.io/text2fx":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}