{"id":"https://openalex.org/W4408354891","doi":"https://doi.org/10.1109/icassp49660.2025.10890164","title":"MorphFader: Enabling Fine-grained Controllable Morphing with Text-to-Audio Models","display_name":"MorphFader: Enabling Fine-grained Controllable Morphing with Text-to-Audio Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354891","doi":"https://doi.org/10.1109/icassp49660.2025.10890164"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890164","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":"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/A5038084030","display_name":"Purnima Kamath","orcid":"https://orcid.org/0000-0003-0351-6574"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Purnima Kamath","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016367573","display_name":"Chitralekha Gupta","orcid":"https://orcid.org/0000-0003-1350-9095"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chitralekha Gupta","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027647989","display_name":"Suranga Nanayakkara","orcid":"https://orcid.org/0000-0001-7441-5493"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Suranga Nanayakkara","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"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":0.9650999903678894,"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":0.9650999903678894,"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/T12290","display_name":"Human Motion and Animation","score":0.920799970626831,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/morphing","display_name":"Morphing","score":0.9632972478866577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.753421425819397},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4361322820186615},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3455284833908081},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3324452042579651}],"concepts":[{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.9632972478866577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753421425819397},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4361322820186615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3455284833908081},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3324452042579651}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890164","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":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1862476492","https://openalex.org/W1901129140","https://openalex.org/W2150307531","https://openalex.org/W2396187157","https://openalex.org/W2593116425","https://openalex.org/W2948978827","https://openalex.org/W2963485731","https://openalex.org/W2972478942","https://openalex.org/W3094550259","https://openalex.org/W3135377667","https://openalex.org/W4226409935","https://openalex.org/W4312933868","https://openalex.org/W4372266552","https://openalex.org/W4375869093","https://openalex.org/W4385245566","https://openalex.org/W4387969125","https://openalex.org/W4396877837","https://openalex.org/W6612017696","https://openalex.org/W6712929052","https://openalex.org/W6736723571","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6841366371","https://openalex.org/W6842854468","https://openalex.org/W6847076894","https://openalex.org/W6849109464","https://openalex.org/W6861353174"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1679315481","https://openalex.org/W3151495635","https://openalex.org/W4385170164","https://openalex.org/W4236870338","https://openalex.org/W2016917053","https://openalex.org/W1580681114","https://openalex.org/W51472912"],"abstract_inverted_index":{"Sound":[0],"morphing":[1,64],"is":[2,45],"the":[3,39,42,77,80,84,109,117,120],"process":[4],"of":[5,41,79,111],"gradually":[6],"and":[7,17,75,103,122],"smoothly":[8],"transforming":[9],"one":[10],"sound":[11,121],"into":[12],"another":[13],"to":[14,114],"generate":[15,123],"novel":[16],"perceptually":[18],"hybrid":[19],"sounds":[20,32,65,93],"that":[21],"simultaneously":[22],"resemble":[23],"both.":[24],"Recently,":[25],"diffusion-based":[26],"text-to-audio":[27,71],"models":[28],"have":[29],"produced":[30],"high-quality":[31],"using":[33,52,70],"text":[34,97],"prompts.":[35,98],"However,":[36],"granularly":[37,115],"controlling":[38],"semantics":[40,118],"sound,":[43],"which":[44],"necessary":[46],"for":[47,63],"morphing,":[48],"can":[49,88],"be":[50],"challenging":[51],"text.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,87,107],"propose":[58],"MorphFader,":[59],"a":[60],"controllable":[61],"method":[62,113],"generated":[66,94],"by":[67,95],"disparate":[68],"prompts":[69],"models.":[72],"By":[73],"intercepting":[74],"interpolating":[76],"components":[78],"cross-attention":[81],"layers":[82],"within":[83],"diffusion":[85],"process,":[86],"create":[89],"smooth":[90,124],"morphs":[91],"between":[92],"different":[96],"Using":[99],"both":[100],"objective":[101],"metrics":[102],"perceptual":[104],"listening":[105],"tests,":[106],"demonstrate":[108],"ability":[110],"our":[112],"control":[116],"in":[119],"morphs.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}