{"id":"https://openalex.org/W4408351912","doi":"https://doi.org/10.1109/icassp49660.2025.10890277","title":"High-Resolution Speech Restoration with Latent Diffusion Model","display_name":"High-Resolution Speech Restoration with Latent Diffusion Model","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351912","doi":"https://doi.org/10.1109/icassp49660.2025.10890277"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890277","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/A5114387566","display_name":"Tushar Dhyani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tushar Dhyani","raw_affiliation_strings":["Sony Europe B.V.,Stuttgart,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Stuttgart,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078880407","display_name":"Florian Lux","orcid":"https://orcid.org/0000-0003-4325-5129"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Lux","raw_affiliation_strings":["University of Stuttgart,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076690986","display_name":"Michele Mancusi","orcid":"https://orcid.org/0000-0003-1591-7076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michele Mancusi","raw_affiliation_strings":["Sony Europe B.V.,Stuttgart,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Stuttgart,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006089763","display_name":"Giorgio Fabbro","orcid":"https://orcid.org/0000-0002-6302-9033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giorgio Fabbro","raw_affiliation_strings":["Sony Europe B.V.,Stuttgart,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Stuttgart,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108862586","display_name":"Fritz Hohl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fritz Hohl","raw_affiliation_strings":["Sony Europe B.V.,Stuttgart,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Stuttgart,Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ngoc Thang Vu","raw_affiliation_strings":["University of Stuttgart,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.96246145,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"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":0.9577999711036682,"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":0.9577999711036682,"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":0.6017544269561768},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46026355028152466},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4207897186279297},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.41444191336631775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32714182138442993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6017544269561768},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46026355028152466},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4207897186279297},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.41444191336631775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32714182138442993},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890277","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":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1964538581","https://openalex.org/W2059045901","https://openalex.org/W2067295501","https://openalex.org/W2071383468","https://openalex.org/W2073979726","https://openalex.org/W2895654193","https://openalex.org/W2998572311","https://openalex.org/W3024869864","https://openalex.org/W3026111682","https://openalex.org/W3092791109","https://openalex.org/W3097945073","https://openalex.org/W3102195007","https://openalex.org/W3147539069","https://openalex.org/W3155072588","https://openalex.org/W3161480375","https://openalex.org/W3196475561","https://openalex.org/W4205689591","https://openalex.org/W4224133928","https://openalex.org/W4281820413","https://openalex.org/W4312933868","https://openalex.org/W4372268522","https://openalex.org/W4375869170","https://openalex.org/W4384080510","https://openalex.org/W4386763928","https://openalex.org/W4386764866","https://openalex.org/W4396877837","https://openalex.org/W4402112296","https://openalex.org/W4408345573","https://openalex.org/W6637568146","https://openalex.org/W6743231993","https://openalex.org/W6744762798","https://openalex.org/W6777664437","https://openalex.org/W6779192484","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6788990321","https://openalex.org/W6798326965","https://openalex.org/W6840200333","https://openalex.org/W6846539466","https://openalex.org/W6847363464","https://openalex.org/W6849109464"],"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":{"Traditional":[0],"speech":[1,93,152],"enhancement":[2],"methods":[3,108],"often":[4],"oversimplify":[5],"the":[6,40,60],"task":[7],"of":[8,16,42,103],"restoration":[9],"by":[10],"focusing":[11],"on":[12,83,144],"a":[13,78,99],"single":[14],"type":[15],"distortion.":[17],"Generative":[18],"models":[19,46],"that":[20,38,109],"handle":[21],"multiple":[22,89],"distortions":[23,90],"frequently":[24],"struggle":[25],"with":[26],"phone":[27],"reconstruction":[28],"and":[29,35,51,91,112,141],"high-frequency":[30],"harmonics,":[31],"leading":[32],"to":[33,56,87,95],"breathing":[34],"gasping":[36],"artifacts":[37],"reduce":[39],"intelligibility":[41],"reconstructed":[43],"speech.":[44],"These":[45],"are":[47,54],"also":[48,135],"computationally":[49],"demanding,":[50],"many":[52],"solutions":[53],"restricted":[55],"producing":[57],"outputs":[58],"in":[59,122,130,138],"wideband":[61],"frequency":[62],"range,":[63],"which":[64],"limits":[65],"their":[66],"suitability":[67],"for":[68,150],"professional":[69],"applications.":[70],"To":[71],"address":[72],"these":[73],"challenges,":[74],"we":[75],"propose":[76],"Hi-ResLDM,":[77],"novel":[79],"generative":[80],"model":[81],"based":[82],"latent":[84],"diffusion":[85],"designed":[86],"remove":[88],"restore":[92],"recordings":[94],"studio":[96],"quality":[97],"at":[98],"full-band":[100],"sampling":[101],"rate":[102],"48kHz.":[104],"Benchmarked":[105],"against":[106],"state-of-the-art":[107],"leverage":[110],"GAN":[111],"Conditional":[113],"Flow":[114],"Matching":[115],"(CFM)":[116],"components,":[117],"Hi-ResLDM":[118,126],"demonstrates":[119],"superior":[120],"performance":[121],"regenerating":[123],"high-frequency-band":[124],"details.":[125],"not":[127],"only":[128],"excels":[129],"non-instrusive":[131],"metrics":[132],"but":[133],"is":[134],"consistently":[136],"preferred":[137],"human":[139],"evaluation":[140],"performs":[142],"competitively":[143],"intrusive":[145],"evaluations,":[146],"making":[147],"it":[148],"ideal":[149],"high-resolution":[151],"restoration.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}