{"id":"https://openalex.org/W4408345948","doi":"https://doi.org/10.1109/icassp49660.2025.10889472","title":"FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillation","display_name":"FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345948","doi":"https://doi.org/10.1109/icassp49660.2025.10889472"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889472","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/A5083693790","display_name":"Jaekwon Im","orcid":null},"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":"Jaekwon Im","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","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,Graduate School of Culture Technology,Daejeon,South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083693790"],"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":0.04026478,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9858999848365784,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9858999848365784,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9785000085830688,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9772999882698059,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6139646172523499},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5729680061340332},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5570399761199951},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5362132787704468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17217430472373962},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10211259126663208},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.07763051986694336},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07030659914016724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6139646172523499},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5729680061340332},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5570399761199951},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5362132787704468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17217430472373962},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10211259126663208},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.07763051986694336},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07030659914016724},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889472","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":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2399742709","https://openalex.org/W3095078764","https://openalex.org/W3095802501","https://openalex.org/W3160652646","https://openalex.org/W3197273793","https://openalex.org/W3197334236","https://openalex.org/W4221155904","https://openalex.org/W4250482878","https://openalex.org/W4281736089","https://openalex.org/W4304099317","https://openalex.org/W4312933868","https://openalex.org/W4387968164","https://openalex.org/W4392903177","https://openalex.org/W4392909842","https://openalex.org/W4400033239","https://openalex.org/W4402111476","https://openalex.org/W4402726956","https://openalex.org/W4402753769","https://openalex.org/W4409347087","https://openalex.org/W4411528087","https://openalex.org/W6640963894","https://openalex.org/W6687506355","https://openalex.org/W6697040288","https://openalex.org/W6732646663","https://openalex.org/W6755977528","https://openalex.org/W6766320909","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6796581206","https://openalex.org/W6802017037","https://openalex.org/W6809884996","https://openalex.org/W6811291704","https://openalex.org/W6840815571","https://openalex.org/W6853515095","https://openalex.org/W6855434424","https://openalex.org/W6865185487","https://openalex.org/W6868481800","https://openalex.org/W6869001559"],"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":{"Versatile":[0],"audio":[1,14,63],"super-resolution":[2,64],"(SR)":[3],"is":[4,99],"the":[5,42,95,113],"challenging":[6],"task":[7],"of":[8,48],"restoring":[9],"high-frequency":[10],"components":[11],"from":[12,37],"low-resolution":[13],"with":[15,78,112],"sampling":[16,49],"rates":[17],"between":[18],"4kHz":[19],"and":[20,29,85,120],"32kHz":[21],"in":[22,117],"various":[23],"domains":[24],"such":[25],"as":[26],"music,":[27],"speech,":[28],"sound":[30],"effects.":[31],"Previous":[32],"diffusion-based":[33],"SR":[34,96,103],"methods":[35],"suffer":[36],"slow":[38],"inference":[39,73],"due":[40],"to":[41],"need":[43],"for":[44,61,102],"a":[45,57],"large":[46],"number":[47],"steps.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"introduce":[55],"FlashSR,":[56],"single-step":[58],"diffusion":[59,76],"model":[60,116],"versatile":[62],"aimed":[65],"at":[66],"producing":[67],"48kHz":[68],"audio.":[69],"FlashSR":[70,108],"achieves":[71],"fast":[72],"by":[74,93],"utilizing":[75],"distillation":[77,81,87],"three":[79],"objectives:":[80],"loss,":[82,84],"adversarial":[83],"distribution-matching":[86],"loss.":[88],"We":[89],"further":[90],"enhance":[91],"performance":[92,111],"proposing":[94],"Vocoder,":[97],"which":[98],"specifically":[100],"designed":[101],"models":[104],"operating":[105],"on":[106],"mel-spectrograms.":[107],"demonstrates":[109],"competitive":[110],"current":[114],"state-of-the-art":[115],"both":[118],"objective":[119],"subjective":[121],"evaluations":[122],"while":[123],"being":[124],"approximately":[125],"22":[126],"times":[127],"faster.":[128]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}