{"id":"https://openalex.org/W4224133928","doi":"https://doi.org/10.21437/interspeech.2022-11026","title":"VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration","display_name":"VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4224133928","doi":"https://doi.org/10.21437/interspeech.2022-11026"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11026","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11026","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.05841","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083342079","display_name":"Haohe Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Haohe Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080214850","display_name":"Xubo Liu","orcid":"https://orcid.org/0000-0002-2558-0959"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018710096","display_name":"Qiao Tian","orcid":"https://orcid.org/0000-0001-8177-7724"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao Tian","raw_affiliation_strings":["Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033866861","display_name":"Yan Zhao","orcid":"https://orcid.org/0000-0001-6431-8665"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Zhao","raw_affiliation_strings":["Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096827899","display_name":"Chuanzeng Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuanzeng Huang","raw_affiliation_strings":["Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100375986","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0002-5743-2029"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5083342079"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":4.4949,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96128423,"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":"4232","last_page":"4236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9782999753952026,"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"}},{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"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/computer-science","display_name":"Computer science","score":0.6668405532836914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6668405532836914}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-11026","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11026","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2204.05841","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.05841","pdf_url":"https://arxiv.org/pdf/2204.05841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.05841","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.05841","pdf_url":"https://arxiv.org/pdf/2204.05841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W2058079016","https://openalex.org/W2121388655","https://openalex.org/W2133665775","https://openalex.org/W2141998673","https://openalex.org/W2757519008","https://openalex.org/W2950391245","https://openalex.org/W2963341071","https://openalex.org/W2963952344","https://openalex.org/W2970006822","https://openalex.org/W2973231102","https://openalex.org/W3015626488","https://openalex.org/W3043119899","https://openalex.org/W3092028330","https://openalex.org/W3093990297","https://openalex.org/W3096159803","https://openalex.org/W3097945073","https://openalex.org/W3102195007","https://openalex.org/W3109064156","https://openalex.org/W3125868443","https://openalex.org/W3145039504","https://openalex.org/W3162109944","https://openalex.org/W3183654341","https://openalex.org/W3197334236","https://openalex.org/W3214281017","https://openalex.org/W4226221107","https://openalex.org/W4286980120","https://openalex.org/W4287326056","https://openalex.org/W4289242435","https://openalex.org/W4295723153","https://openalex.org/W4297789187"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Speech":[0],"restoration":[1,47],"aims":[2],"to":[3,44,49,90],"remove":[4],"distortions":[5,34,72],"in":[6,36],"speech":[7,21,26,46,65,69,82,143],"signals.":[8],"Prior":[9],"methods":[10],"mainly":[11],"focus":[12],"on":[13,100,135],"a":[14,60,87,115,122],"single":[15],"type":[16],"of":[17,146],"distortion,":[18],"such":[19,139],"as":[20,140],"denoising":[22],"or":[23],"dereverberation.":[24],"However,":[25],"signals":[27],"can":[28,79],"be":[29],"degraded":[30,81,111,137],"by":[31],"several":[32],"different":[33],"simultaneously":[35],"the":[37,110],"real":[38],"world.":[39],"It":[40],"is":[41,133],"thus":[42],"important":[43],"extend":[45],"models":[48],"deal":[50],"with":[51,86],"multiple":[52,71],"distortions.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"introduce":[58],"VoiceFixer,":[59],"unified":[61],"framework":[62],"for":[63],"high-fidelity":[64,94],"restoration.":[66],"VoiceFixer":[67,98,132,147],"restores":[68],"from":[70,109],"(e.g.,":[73,83],"noise,":[74],"reverberation,":[75],"and":[76,78,113,127],"clipping)":[77],"expand":[80],"noisy":[84],"speech)":[85],"low":[88],"bandwidth":[89],"44.1":[91],"kHz":[92],"full-bandwidth":[93],"speech.":[95],"We":[96],"design":[97],"based":[99],"(1)":[101],"an":[102],"analysis":[103],"stage":[104,117],"that":[105,118,131],"predicts":[106],"intermediate-level":[107],"features":[108],"speech,":[112,138],"(2)":[114],"synthesis":[116],"generates":[119],"waveform":[120],"using":[121],"neural":[123],"vocoder.":[124],"Both":[125],"objective":[126],"subjective":[128],"evaluations":[129],"show":[130],"effective":[134],"severely":[136],"real-world":[141],"historical":[142],"recordings.":[144],"Samples":[145],"are":[148],"available":[149],"at":[150],"https://haoheliu.github.io/voicefixer.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":10}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}