{"id":"https://openalex.org/W3197990672","doi":"https://doi.org/10.21437/interspeech.2021-892","title":"WSRGlow: A Glow-Based Waveform Generative Model for Audio Super-Resolution","display_name":"WSRGlow: A Glow-Based Waveform Generative Model for Audio Super-Resolution","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197990672","doi":"https://doi.org/10.21437/interspeech.2021-892","mag":"3197990672"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-892","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","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/A5053856461","display_name":"Kexun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kexun Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088179161","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-9889-5460"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028104073","display_name":"Changliang Xu","orcid":"https://orcid.org/0000-0002-8976-6832"},"institutions":[{"id":"https://openalex.org/I4210147194","display_name":"Convergence","ror":"https://ror.org/03kcznq08","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210147194"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changliang Xu","raw_affiliation_strings":["State Key Laboratory of Media Convergence Production Technology and Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Media Convergence Production Technology and Systems","institution_ids":["https://openalex.org/I4210147194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1649","last_page":"1653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9894999861717224,"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":0.9894999861717224,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9876000285148621,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7562060356140137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6564537286758423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5089421272277832},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.47595998644828796},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.41103237867355347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3564836382865906},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1295478343963623}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7562060356140137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6564537286758423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5089421272277832},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47595998644828796},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.41103237867355347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3564836382865906},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1295478343963623},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-892","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1989337816","https://openalex.org/W2070126272","https://openalex.org/W2134017361","https://openalex.org/W2135567392","https://openalex.org/W2399742709","https://openalex.org/W2407134240","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2802034954","https://openalex.org/W2919362165","https://openalex.org/W2940120659","https://openalex.org/W2944438111","https://openalex.org/W2946200149","https://openalex.org/W2952711665","https://openalex.org/W2963300588","https://openalex.org/W2963952344","https://openalex.org/W2970855822","https://openalex.org/W3033411150","https://openalex.org/W3035649147","https://openalex.org/W3047866127","https://openalex.org/W3081279708","https://openalex.org/W3095495550","https://openalex.org/W3095545636","https://openalex.org/W3095802501","https://openalex.org/W3169635929","https://openalex.org/W4205227948"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W3156291593","https://openalex.org/W2893763841","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W2778699561","https://openalex.org/W2995996972","https://openalex.org/W2312116756","https://openalex.org/W3128571556","https://openalex.org/W3024390022"],"abstract_inverted_index":{"Audio":[0],"super-resolution":[1],"is":[2,139,156],"the":[3,18,87,91,103,121,125,136,145,158],"task":[4],"of":[5,53,90,150],"constructing":[6],"a":[7,12,51,69],"highresolution":[8],"(HR)":[9],"audio":[10,15,76,94,104,113],"from":[11,106,124,165],"low-resolution":[13,107],"(LR)":[14],"by":[16],"adding":[17],"missing":[19],"band.Previous":[20],"methods":[21],"based":[22],"on":[23,96],"convolutional":[24],"neural":[25],"networks":[26],"and":[27,45,61,82,99,115,128,143,153],"mean":[28],"squared":[29],"error":[30],"training":[31,60],"objective":[32,152],"have":[33],"relatively":[34],"low":[35],"performance,":[36,58],"while":[37],"adversarial":[38],"generative":[39,72],"models":[40],"are":[41,170],"difficult":[42],"to":[43,74,84,101,141,161],"train":[44,142],"tune.Recently,":[46],"normalizing":[47],"flow":[48],"has":[49],"attracted":[50],"lot":[52],"attention":[54],"for":[55],"its":[56],"high":[57],"simple":[59],"fast":[62],"inference.In":[63],"this":[64],"paper,":[65],"we":[66,79,109],"propose":[67,110],"WSRGlow,":[68],"Glow-based":[70],"waveform":[71],"model":[73,138,160],"perform":[75],"super-resolution.Specifically,":[77],"1)":[78],"integrate":[80],"WaveNet":[81],"Glow":[83],"directly":[85],"maximize":[86],"exact":[88],"likelihood":[89],"target":[92],"HR":[93],"conditioned":[95],"LR":[97,112,122,167],"information;":[98],"2)":[100],"exploit":[102],"information":[105,123],"audio,":[108],"an":[111,116],"encoder":[114],"STFT":[117],"encoder,":[118],"which":[119],"encode":[120],"time":[126],"domain":[127,130],"frequency":[129],"respectively.The":[131],"experimental":[132],"results":[133],"show":[134],"that":[135],"proposed":[137],"easier":[140],"outperforms":[144],"previous":[146],"works":[147],"in":[148],"terms":[149],"both":[151],"perceptual":[154],"quality.WSRGlow":[155],"also":[157],"first":[159],"produce":[162],"48kHz":[163],"waveforms":[164],"12kHz":[166],"audio.Audio":[168],"samples":[169],"available":[171],"at":[172],"https://zkx06111.github.io/wsrglow/.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}