{"id":"https://openalex.org/W4375869358","doi":"https://doi.org/10.1109/icassp49357.2023.10095103","title":"Conditioning and Sampling in Variational Diffusion Models for Speech Super-Resolution","display_name":"Conditioning and Sampling in Variational Diffusion Models for Speech Super-Resolution","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869358","doi":"https://doi.org/10.1109/icassp49357.2023.10095103"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095103","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067730834","display_name":"Chin-Yun Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Chin-Yun Yu","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK","Centre for Digital Music, Queen Mary University of London, UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016912114","display_name":"Sung-Lin Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","KR"],"is_corresponding":false,"raw_author_name":"Sung-Lin Yeh","raw_affiliation_strings":["University of Edinburgh,Institute for Language, Cognition and Computation,UK","Institute for Language, Cognition and Computation, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Institute for Language, Cognition and Computation,UK","institution_ids":["https://openalex.org/I4210107233"]},{"raw_affiliation_string":"Institute for Language, Cognition and Computation, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032485940","display_name":"Gy\u00f6rgy Fazekas","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gy\u00f6rgy Fazekas","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,UK","Centre for Digital Music, Queen Mary University of London, UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101745105","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-6197-0874"},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","KR"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["University of Edinburgh,Institute for Language, Cognition and Computation,UK","Institute for Language, Cognition and Computation, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Institute for Language, Cognition and Computation,UK","institution_ids":["https://openalex.org/I4210107233"]},{"raw_affiliation_string":"Institute for Language, Cognition and Computation, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067730834"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":2.3564,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90457114,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9865000247955322,"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":0.9865000247955322,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.9785000085830688,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7367990016937256},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7017643451690674},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7009325623512268},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6267414689064026},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.601384162902832},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5441759824752808},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5390111804008484},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4638194441795349},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4370208978652954},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.43160104751586914},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.41217291355133057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35792839527130127},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3576275706291199},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2106671929359436},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12071061134338379},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10554814338684082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367990016937256},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7017643451690674},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7009325623512268},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6267414689064026},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.601384162902832},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5441759824752808},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5390111804008484},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4638194441795349},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4370208978652954},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43160104751586914},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.41217291355133057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35792839527130127},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3576275706291199},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2106671929359436},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12071061134338379},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10554814338684082},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"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/icassp49357.2023.10095103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095103","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311061","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W2129069237","https://openalex.org/W2963300588","https://openalex.org/W2998572311","https://openalex.org/W3036167779","https://openalex.org/W3110257065","https://openalex.org/W3123097577","https://openalex.org/W3125868443","https://openalex.org/W3129651364","https://openalex.org/W3177150392","https://openalex.org/W3184410885","https://openalex.org/W3197334236","https://openalex.org/W3197990672","https://openalex.org/W3207575373","https://openalex.org/W4225759859","https://openalex.org/W4281872541","https://openalex.org/W4283215837","https://openalex.org/W4297778191","https://openalex.org/W4297841790","https://openalex.org/W4312497550","https://openalex.org/W6631190155","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6786375611","https://openalex.org/W6797906067","https://openalex.org/W6798721538","https://openalex.org/W6803078664"],"related_works":["https://openalex.org/W2022538999","https://openalex.org/W1955763106","https://openalex.org/W2002243964","https://openalex.org/W3090086172","https://openalex.org/W3171883019","https://openalex.org/W1585241115","https://openalex.org/W2120213246","https://openalex.org/W1564179349","https://openalex.org/W2025188156","https://openalex.org/W2117625637"],"abstract_inverted_index":{"Recently,":[0],"diffusion":[1],"models":[2],"(DMs)":[3],"have":[4],"been":[5],"increasingly":[6],"used":[7],"in":[8],"audio":[9,56],"processing":[10],"tasks,":[11],"including":[12],"speech":[13,24],"super-resolution":[14],"(SR),":[15],"which":[16],"aims":[17],"to":[18,105,113],"restore":[19],"high-frequency":[20],"content":[21],"given":[22],"low-resolution":[23,38,55],"utterances.":[25],"This":[26],"is":[27],"commonly":[28],"achieved":[29],"by":[30,88],"conditioning":[31],"the":[32,51,54,58,73,81,84,90,126],"network":[33],"of":[34,53,62,83,117],"noise":[35,107],"predictor":[36],"with":[37,94,101,130],"audio.":[39],"In":[40],"this":[41,131],"paper,":[42],"we":[43,109],"propose":[44],"a":[45,69,99,114],"novel":[46,132],"sampling":[47,60,75,92],"algorithm":[48],"that":[49],"communicates":[50],"information":[52],"via":[57],"reverse":[59],"process":[61,76],"DMs.":[63],"The":[64],"proposed":[65,91],"method":[66,93],"can":[67,78,110],"be":[68],"drop-in":[70],"replacement":[71],"for":[72],"vanilla":[74],"and":[77],"significantly":[79],"improve":[80],"performance":[82],"existing":[85],"works.":[86],"Moreover,":[87],"coupling":[89],"an":[95],"unconditional":[96],"DM,":[97],"i.e.,":[98],"DM":[100],"no":[102],"auxiliary":[103],"inputs":[104],"its":[106],"predictor,":[108],"generalize":[111],"it":[112],"wide":[115],"range":[116],"SR":[118],"setups.":[119],"We":[120],"also":[121],"attain":[122],"state-of-the-art":[123],"results":[124],"on":[125],"VCTK":[127],"Multi-Speaker":[128],"benchmark":[129],"formulation.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}