{"id":"https://openalex.org/W4221155904","doi":"https://doi.org/10.21437/interspeech.2022-11017","title":"Neural Vocoder is All You Need for Speech Super-resolution","display_name":"Neural Vocoder is All You Need for Speech Super-resolution","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221155904","doi":"https://doi.org/10.21437/interspeech.2022-11017"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11017","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11017","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.14941","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"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":"Haohe Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"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/A5027289427","display_name":"Woosung Choi","orcid":"https://orcid.org/0000-0002-7001-3099"},"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":"Woosung Choi","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, UK"],"raw_orcid":null,"affiliations":[{"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/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"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music Intelligence (SAMI) Group, ByteDance, China","institution_ids":[]}]},{"author_position":"last","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":true,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051837453"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4227","last_page":"4231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.750377893447876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6821044683456421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3399444818496704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750377893447876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6821044683456421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3399444818496704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-11017","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11017","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:2203.14941","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.14941","pdf_url":"https://arxiv.org/pdf/2203.14941","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:2203.14941","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.14941","pdf_url":"https://arxiv.org/pdf/2203.14941","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1517841224","https://openalex.org/W1522301498","https://openalex.org/W1591013319","https://openalex.org/W1836465849","https://openalex.org/W2100285470","https://openalex.org/W2122336353","https://openalex.org/W2308367698","https://openalex.org/W2407774997","https://openalex.org/W2802034954","https://openalex.org/W2940120659","https://openalex.org/W2963952344","https://openalex.org/W2983519761","https://openalex.org/W2998639482","https://openalex.org/W3092028330","https://openalex.org/W3093990297","https://openalex.org/W3095802501","https://openalex.org/W3109064156","https://openalex.org/W3125868443","https://openalex.org/W3197334236","https://openalex.org/W3203491020","https://openalex.org/W3214281017","https://openalex.org/W4226221107","https://openalex.org/W4286980120","https://openalex.org/W4287118891","https://openalex.org/W4295336863"],"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/W2368779261","https://openalex.org/W2778699561"],"abstract_inverted_index":{"Speech":[0],"super-resolution":[1,55],"(SR)":[2],"is":[3,131],"a":[4,27,50,61,72,76,81,116,141],"task":[5],"to":[6,37],"increase":[7],"speech":[8,16,54,134],"sampling":[9],"rate":[10],"by":[11,105,136],"generating":[12],"high-frequency":[13],"components.":[14],"Existing":[15],"SR":[17,135],"methods":[18],"are":[19],"trained":[20],"in":[21,41,127,149],"constrained":[22],"experimental":[23],"settings,":[24],"such":[25],"as":[26],"fixed":[28],"upsampling":[29,67],"ratio.":[30],"These":[31],"strong":[32],"constraints":[33],"can":[34,59,146],"potentially":[35],"lead":[36],"poor":[38],"generalization":[39],"ability":[40],"mismatched":[42],"real-world":[43],"cases.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"neural":[51,77],"vocoder":[52,78,130],"based":[53],"method":[56],"(NVSR)":[57],"that":[58,124],"handle":[60],"variety":[62],"of":[63,71],"input":[64],"resolution":[65],"and":[66,80,103,107,114],"ratios.":[68],"NVSR":[69,100],"consists":[70],"mel-bandwidth":[73,138],"extension":[74,139],"module,":[75,79],"post-processing":[82],"module.":[83],"Our":[84],"proposed":[85],"system":[86],"achieves":[87,115],"state-of-the-art":[88],"results":[89],"on":[90,110],"the":[91,128],"VCTK":[92],"multi-speaker":[93],"benchmark.":[94],"On":[95],"44.1":[96],"kHz":[97],"target":[98],"resolution,":[99],"outperforms":[101],"WSRGlow":[102],"Nu-wave":[104],"8%":[106],"37%":[108],"respectively":[109],"log":[111],"spectral":[112],"distance":[113],"significantly":[117],"better":[118],"perceptual":[119],"quality.":[120],"We":[121],"also":[122],"demonstrate":[123],"prior":[125],"knowledge":[126],"pre-trained":[129],"crucial":[132],"for":[133],"performing":[137],"with":[140],"simple":[142],"replication-padding":[143],"method.":[144],"Samples":[145],"be":[147],"found":[148],"https://haoheliu.github.io/nvsr.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}