{"id":"https://openalex.org/W3197912330","doi":"https://doi.org/10.21437/interspeech.2021-599","title":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","display_name":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197912330","doi":"https://doi.org/10.21437/interspeech.2021-599","mag":"3197912330"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-599","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-599","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/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Szu-Wei Fu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058798840","display_name":"Cheng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng Yu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060785253","display_name":"Tsun-An Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsun-An Hsieh","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055583643","display_name":"Peter Plantinga","orcid":null},"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":"Peter Plantinga","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040811098","display_name":"Mirco Ravanelli","orcid":"https://orcid.org/0000-0002-3929-5526"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mirco Ravanelli","raw_affiliation_strings":["Mila-Quebec AI Institute, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila-Quebec AI Institute, Montreal, Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044008055"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":22.7416,"has_fulltext":false,"cited_by_count":199,"citation_normalized_percentile":{"value":0.99820541,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"201","last_page":"205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9961000084877014,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9771000146865845,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/speech-enhancement","display_name":"Speech enhancement","score":0.7603840231895447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6753774881362915},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5824601650238037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28690171241760254},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0677725076675415}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7603840231895447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6753774881362915},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5824601650238037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28690171241760254},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0677725076675415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-599","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-599","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":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1673923490","https://openalex.org/W1897240248","https://openalex.org/W2067295501","https://openalex.org/W2145339207","https://openalex.org/W2603567530","https://openalex.org/W2696558042","https://openalex.org/W2785678896","https://openalex.org/W2802304149","https://openalex.org/W2805233667","https://openalex.org/W2891607145","https://openalex.org/W2892110446","https://openalex.org/W2892129657","https://openalex.org/W2902072693","https://openalex.org/W2912191105","https://openalex.org/W2940177920","https://openalex.org/W2949558265","https://openalex.org/W2962866211","https://openalex.org/W2962998773","https://openalex.org/W2963341071","https://openalex.org/W2963351212","https://openalex.org/W2963403924","https://openalex.org/W2964067969","https://openalex.org/W2964280870","https://openalex.org/W2987989623","https://openalex.org/W2998161426","https://openalex.org/W3015219411","https://openalex.org/W3016050488","https://openalex.org/W3017350693","https://openalex.org/W3035810926","https://openalex.org/W3096159803","https://openalex.org/W3096217733","https://openalex.org/W3096949857","https://openalex.org/W3097934054","https://openalex.org/W3097945073","https://openalex.org/W3161480375","https://openalex.org/W3163827866"],"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/W3096184950","https://openalex.org/W2770665941","https://openalex.org/W2782782444"],"abstract_inverted_index":{"The":[0],"discrepancy":[1],"between":[2],"the":[3,19,39,52,58,61,69,98,112],"cost":[4],"function":[5],"used":[6],"for":[7],"training":[8,84],"a":[9,35,55,79],"speech":[10,23,89],"enhancement":[11],"model":[12],"and":[13,115],"human":[14,29],"auditory":[15],"perception":[16,30],"usually":[17],"makes":[18],"quality":[20],"of":[21,60,88],"enhanced":[22],"unsatisfactory.Objective":[24],"evaluation":[25,63],"metrics":[26,49,70],"which":[27,82],"consider":[28],"can":[31,71,104],"hence":[32],"serve":[33],"as":[34],"bridge":[36],"to":[37,46,111],"reduce":[38],"gap.Our":[40],"previously":[41],"proposed":[42],"MetricGAN":[43,114],"was":[44],"designed":[45],"optimize":[47],"objective":[48],"by":[50,108],"connecting":[51],"metric":[53],"with":[54],"discriminator.Because":[56],"only":[57],"scores":[59],"target":[62],"functions":[64],"are":[65,91],"needed":[66],"during":[67],"training,":[68],"even":[72],"be":[73],"non-differentiable.In":[74],"this":[75],"study,":[76],"we":[77],"propose":[78],"MetricGAN+":[80,103],"in":[81],"three":[83],"techniques":[85],"incorporating":[86],"domainknowledge":[87],"processing":[90],"proposed.With":[92],"these":[93],"techniques,":[94],"experimental":[95],"results":[96,118],"on":[97],"VoiceBank-DEMAND":[99],"dataset":[100],"show":[101],"that":[102],"increase":[105],"PESQ":[106],"score":[107,120],"0.3":[109],"compared":[110],"previous":[113],"achieve":[116],"stateof-the-art":[117],"(PESQ":[119],"=":[121],"3.15).":[122]},"counts_by_year":[{"year":2026,"cited_by_count":20},{"year":2025,"cited_by_count":53},{"year":2024,"cited_by_count":47},{"year":2023,"cited_by_count":49},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":4}],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2025-10-10T00:00:00"}