{"id":"https://openalex.org/W3096159803","doi":"https://doi.org/10.21437/interspeech.2020-2143","title":"HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks","display_name":"HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096159803","doi":"https://doi.org/10.21437/interspeech.2020-2143","mag":"3096159803"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2143","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5101859099","display_name":"Jiaqi Su","orcid":"https://orcid.org/0000-0001-6038-0808"},"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"]},{"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":"Jiaqi Su","raw_affiliation_strings":["Adobe Research","Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Princeton University","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":127,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4506","last_page":"4510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9908000230789185,"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":0.9850999712944031,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7493821382522583},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.6886197328567505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6515430212020874},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5727003812789917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5469652414321899},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.47384506464004517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35992199182510376},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.18509840965270996},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16356831789016724},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08687716722488403}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7493821382522583},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.6886197328567505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6515430212020874},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5727003812789917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5469652414321899},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.47384506464004517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35992199182510376},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.18509840965270996},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16356831789016724},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08687716722488403}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2143","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1989314204","https://openalex.org/W2006129368","https://openalex.org/W2044893557","https://openalex.org/W2086381917","https://openalex.org/W2153894152","https://openalex.org/W2164502538","https://openalex.org/W2401258970","https://openalex.org/W2408467190","https://openalex.org/W2410879554","https://openalex.org/W2519091744","https://openalex.org/W2555915854","https://openalex.org/W2577946330","https://openalex.org/W2603567530","https://openalex.org/W2711335087","https://openalex.org/W2747161606","https://openalex.org/W2800675406","https://openalex.org/W2805669069","https://openalex.org/W2889335976","https://openalex.org/W2911394281","https://openalex.org/W2940290905","https://openalex.org/W2940385941","https://openalex.org/W2949558265","https://openalex.org/W2963103134","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963452667","https://openalex.org/W2963920537","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2971646704","https://openalex.org/W2972443522","https://openalex.org/W2987989623","https://openalex.org/W2996286887","https://openalex.org/W2998678989","https://openalex.org/W3015676952","https://openalex.org/W3102190437","https://openalex.org/W3147539069","https://openalex.org/W4286800003","https://openalex.org/W4289242435","https://openalex.org/W4394668580"],"related_works":["https://openalex.org/W2971455341","https://openalex.org/W2963258858","https://openalex.org/W4288343117","https://openalex.org/W3005226846","https://openalex.org/W2468514837","https://openalex.org/W4225288502","https://openalex.org/W4226051017","https://openalex.org/W4306789193","https://openalex.org/W3208312582","https://openalex.org/W4226067002"],"abstract_inverted_index":{"Real-world":[0],"audio":[1],"recordings":[2],"are":[3],"often":[4],"degraded":[5],"by":[6],"factors":[7],"such":[8],"as":[9,28],"noise,":[10],"reverberation,":[11],"and":[12,53,85,96],"equalization":[13],"distortion.This":[14],"paper":[15],"introduces":[16],"HiFi-GAN,":[17],"a":[18,35],"deep":[19,60],"learning":[20],"method":[21],"to":[22,26,67,79],"transform":[23],"recorded":[24,33],"speech":[25,83],"sound":[27],"though":[29],"it":[30],"had":[31],"been":[32],"in":[34,48,93],"studio.We":[36],"use":[37],"an":[38],"end-to-end":[39],"feed-forward":[40],"WaveNet":[41],"architecture,":[42],"trained":[43],"with":[44],"multi-scale":[45],"adversarial":[46],"discriminators":[47,66],"both":[49,94],"the":[50,54,59,65,69],"time":[51],"domain":[52],"time-frequency":[55],"domain.It":[56],"relies":[57],"on":[58],"feature":[61],"matching":[62],"losses":[63],"of":[64,72],"improve":[68],"perceptual":[70],"quality":[71],"enhanced":[73],"speech.The":[74],"proposed":[75],"model":[76],"generalizes":[77],"well":[78],"new":[80,82,86],"speakers,":[81],"content,":[84],"environments.It":[87],"significantly":[88],"outperforms":[89],"state-of-the-art":[90],"baseline":[91],"methods":[92],"objective":[95],"subjective":[97],"experiments.":[98]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}