{"id":"https://openalex.org/W4200483526","doi":"https://doi.org/10.1109/waspaa52581.2021.9632770","title":"HiFi-GAN-2: Studio-Quality Speech Enhancement via Generative Adversarial Networks Conditioned on Acoustic Features","display_name":"HiFi-GAN-2: Studio-Quality Speech Enhancement via Generative Adversarial Networks Conditioned on Acoustic Features","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4200483526","doi":"https://doi.org/10.1109/waspaa52581.2021.9632770"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5101859099","display_name":"Jiaqi Su","orcid":"https://orcid.org/0000-0001-6038-0808"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiaqi Su","raw_affiliation_strings":["Princeton University,USA","Princeton University, USA"],"affiliations":[{"raw_affiliation_string":"Princeton University,USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research,USA","Adobe Research, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research,USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Research, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034842939","display_name":"Adam Finkelstein","orcid":"https://orcid.org/0000-0001-9422-5363"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Finkelstein","raw_affiliation_strings":["Princeton University,USA","Princeton University, USA"],"affiliations":[{"raw_affiliation_string":"Princeton University,USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101859099"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":5.5551,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.96857659,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"166","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8205549716949463},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6450932621955872},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6375042796134949},{"id":"https://openalex.org/keywords/studio","display_name":"Studio","score":0.5836580991744995},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5458803772926331},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.509804904460907},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.49883222579956055},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.46704545617103577},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.45433762669563293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.261435329914093},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13908866047859192},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.069599449634552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205549716949463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6450932621955872},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6375042796134949},{"id":"https://openalex.org/C45012715","wikidata":"https://www.wikidata.org/wiki/Q746628","display_name":"Studio","level":2,"score":0.5836580991744995},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5458803772926331},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.509804904460907},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.49883222579956055},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.46704545617103577},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.45433762669563293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.261435329914093},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13908866047859192},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.069599449634552},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1989314204","https://openalex.org/W2006129368","https://openalex.org/W2030931454","https://openalex.org/W2044893557","https://openalex.org/W2410879554","https://openalex.org/W2519091744","https://openalex.org/W2555915854","https://openalex.org/W2711335087","https://openalex.org/W2726515241","https://openalex.org/W2757519008","https://openalex.org/W2805669069","https://openalex.org/W2889335976","https://openalex.org/W2940385941","https://openalex.org/W2940807449","https://openalex.org/W2949558265","https://openalex.org/W2963103134","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972785266","https://openalex.org/W2991361823","https://openalex.org/W3015626488","https://openalex.org/W3096159803","https://openalex.org/W3096408984","https://openalex.org/W3097034112","https://openalex.org/W3097934054","https://openalex.org/W3097945073","https://openalex.org/W3160085755","https://openalex.org/W3160652646","https://openalex.org/W3163296124","https://openalex.org/W3197042120","https://openalex.org/W4289242435","https://openalex.org/W4297789187","https://openalex.org/W6651792446","https://openalex.org/W6756251360","https://openalex.org/W6762114000","https://openalex.org/W6767111847","https://openalex.org/W6770232298","https://openalex.org/W6779126078","https://openalex.org/W6788379279"],"related_works":["https://openalex.org/W392621609","https://openalex.org/W2537599345","https://openalex.org/W3016102847","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2358925824","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Modern":[0],"speech":[1,30,50,209],"content":[2,210],"creation":[3],"tasks":[4],"such":[5,41],"as":[6,42,47,91,187,189],"podcasts,":[7],"video":[8],"voice-overs,":[9],"and":[10,19,44,52,73,111,165,172,192,213],"audio":[11,15],"books":[12],"require":[13],"studio-quality":[14,145,169],"with":[16,69],"full":[17],"bandwidth":[18,138],"balanced":[20],"equalization":[21],"(EQ).":[22],"These":[23],"goals":[24],"pose":[25],"a":[26,57,87,93,102,121,131,136],"challenge":[27],"for":[28],"conventional":[29,185],"enhancement":[31,59],"methods,":[32],"which":[33],"typically":[34],"focus":[35],"on":[36,113,183,207],"removing":[37],"significant":[38],"acoustic":[39,98],"degradation":[40],"noise":[43],"reverb":[45,72,164],"so":[46],"to":[48,76,168,204],"improve":[49],"clarity":[51],"intelligibility.":[53],"We":[54],"present":[55],"HiFi-GAN-2,":[56],"waveform-to-waveform":[58],"method":[60,179,201],"that":[61,176,199],"improves":[62],"the":[63,97,107,114,118,142,148,152,177,214],"quality":[64,206],"of":[65,101,151,162],"real-world":[66,208],"consumer-grade":[67],"recordings,":[68],"moderate":[70],"noise,":[71,163],"EQ":[74,166],"distortion,":[75],"sound":[77],"like":[78],"studio":[79,205],"recordings.":[80],"HiFi-GAN-2":[81],"has":[82],"three":[83],"components.":[84],"First,":[85],"given":[86,106],"noisy":[88,109],"reverberant":[89],"recording":[90],"input,":[92,110],"recurrent":[94],"network":[95,140],"predicts":[96],"features":[99],"(MFCCs)":[100],"clean":[103,132],"signal.":[104,134],"Second,":[105],"same":[108],"conditioned":[112],"MFCCs":[115],"output":[116,150],"by":[117],"first":[119],"network,":[120],"feed-forward":[122],"WaveNet":[123],"(modeled":[124],"via":[125,160],"multidomain":[126],"multi-scale":[127],"adversarial":[128],"training)":[129],"generates":[130,141],"16kHz":[133,149],"Third,":[135],"pre-trained":[137],"extension":[139],"final":[143],"48kHz":[144],"signal":[146],"from":[147],"second":[153],"network.":[154],"The":[155],"complete":[156],"pipeline":[157],"is":[158],"trained":[159],"simulation":[161],"added":[167],"speech.":[170],"Objective":[171],"subjective":[173],"evaluations":[174],"show":[175,198],"proposed":[178],"outperforms":[180],"state-of-the-art":[181],"baselines":[182],"both":[184],"denoising":[186,193],"well":[188],"joint":[190],"dereverberation":[191],"tasks.":[194],"Listening":[195],"tests":[196],"also":[197],"our":[200],"achieves":[202],"close":[203],"(TED":[211],"Talks":[212],"VoxCeleb":[215],"dataset).":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":8}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
