{"id":"https://openalex.org/W4372341905","doi":"https://doi.org/10.1109/icassp49357.2023.10095637","title":"Solving Audio Inverse Problems with a Diffusion Model","display_name":"Solving Audio Inverse Problems with a Diffusion Model","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341905","doi":"https://doi.org/10.1109/icassp49357.2023.10095637"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/10332235-bd5c-4421-9982-730c413fabfd","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030929567","display_name":"Eloi Moliner","orcid":"https://orcid.org/0000-0001-5719-326X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Eloi Moliner","raw_affiliation_strings":["Aalto University,Acoustics Lab,Dept. of Information & Communications Eng.,Espoo,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Acoustics Lab,Dept. of Information & Communications Eng.,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103009697","display_name":"Jaakko Lehtinen","orcid":"https://orcid.org/0000-0001-9418-4944"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jaakko Lehtinen","raw_affiliation_strings":["Aalto University,Dept. of Computer Science,Espoo,Finland","Dept. of Computer Science, Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Dept. of Computer Science,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Dept. of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021963945","display_name":"Vesa V\u00e4lim\u00e4ki","orcid":"https://orcid.org/0000-0002-7869-292X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Vesa V\u00e4lim\u00e4ki","raw_affiliation_strings":["Aalto University,Acoustics Lab,Dept. of Information & Communications Eng.,Espoo,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Acoustics Lab,Dept. of Information & Communications Eng.,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9402,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96515916,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"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":0.9969000220298767,"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":0.9969000220298767,"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/T10860","display_name":"Speech and Audio Processing","score":0.9933000206947327,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/diffusion","display_name":"Diffusion","score":0.6608985662460327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6565675139427185},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5076779127120972},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1645691692829132},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08250284194946289}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6608985662460327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6565675139427185},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5076779127120972},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1645691692829132},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08250284194946289},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/123888","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/10332235-bd5c-4421-9982-730c413fabfd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/123888","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/10332235-bd5c-4421-9982-730c413fabfd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2112390905","https://openalex.org/W2222562092","https://openalex.org/W2740337320","https://openalex.org/W2760103357","https://openalex.org/W2891148495","https://openalex.org/W2950547518","https://openalex.org/W2963889406","https://openalex.org/W3015289235","https://openalex.org/W3022195800","https://openalex.org/W3035574324","https://openalex.org/W3036167779","https://openalex.org/W3036843665","https://openalex.org/W3102195007","https://openalex.org/W3110257065","https://openalex.org/W3129651364","https://openalex.org/W3170094039","https://openalex.org/W3191805365","https://openalex.org/W3211976544","https://openalex.org/W4225759859","https://openalex.org/W4281820413","https://openalex.org/W4281872541","https://openalex.org/W4281969232","https://openalex.org/W4282913091","https://openalex.org/W4283215837","https://openalex.org/W4285412734","https://openalex.org/W4287072584","https://openalex.org/W4298184813","https://openalex.org/W4310695675","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4320235053","https://openalex.org/W4320459320","https://openalex.org/W4380434618","https://openalex.org/W6676976081","https://openalex.org/W6755182157","https://openalex.org/W6757028937","https://openalex.org/W6779823529","https://openalex.org/W6780179280","https://openalex.org/W6783182287","https://openalex.org/W6786375611","https://openalex.org/W6796762324","https://openalex.org/W6797004501","https://openalex.org/W6798855526","https://openalex.org/W6809940947","https://openalex.org/W6810793953","https://openalex.org/W6838452192","https://openalex.org/W6839052650","https://openalex.org/W6839133533","https://openalex.org/W6841733230","https://openalex.org/W6844364769","https://openalex.org/W6849956205","https://openalex.org/W6850178718"],"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":[0,45,123],"paper":[1],"presents":[2],"CQT-Diff,":[3],"a":[4,23,28],"data-driven":[5],"generative":[6],"audio":[7,19,88,106,119,136],"model":[8,31,51],"that":[9,35,97],"can,":[10],"once":[11],"trained,":[12],"be":[13],"used":[14],"for":[15,131],"solving":[16,132],"various":[17],"different":[18,84],"inverse":[20,133],"problems":[21,134],"in":[22,43,82,105,118,135],"problem-agnostic":[24],"setting.":[25],"CQT-Diff":[26,98],"is":[27,36,46,71],"neural":[29],"diffusion":[30],"with":[32,52,73],"an":[33,53],"architecture":[34],"carefully":[37],"constructed":[38],"to":[39],"exploit":[40],"pitch-equivariant":[41],"symmetries":[42],"music.":[44],"achieved":[47],"by":[48],"preconditioning":[49],"the":[50,100,126],"invertible":[54],"Constant-Q":[55],"Transform":[56],"(CQT),":[57],"whose":[58],"logarithmically-spaced":[59],"frequency":[60],"axis":[61],"represents":[62,125],"pitch":[63],"equivariance":[64],"as":[65],"translation":[66],"equivariance.":[67],"The":[68,94],"proposed":[69],"method":[70],"evaluated":[72],"solo":[74],"piano":[75],"music,":[76],"using":[77],"objective":[78],"and":[79,85,92,103,121],"subjective":[80],"metrics":[81],"three":[83],"varied":[86],"tasks:":[87],"bandwidth":[89,107],"extension,":[90],"inpainting,":[91],"declipping.":[93,122],"results":[95],"show":[96],"outperforms":[99],"compared":[101],"baselines":[102,117],"ablations":[104],"extension":[108],"and,":[109],"without":[110],"retraining,":[111],"delivers":[112],"competitive":[113],"performance":[114],"against":[115],"modern":[116],"inpainting":[120],"work":[124],"first":[127],"diffusion-based":[128],"general":[129],"framework":[130],"processing.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}