{"id":"https://openalex.org/W4408352776","doi":"https://doi.org/10.1109/icassp49660.2025.10890696","title":"Reexamining the Efficacy of MetricGAN for Speech Enhancement","display_name":"Reexamining the Efficacy of MetricGAN for Speech Enhancement","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352776","doi":"https://doi.org/10.1109/icassp49660.2025.10890696"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101474128","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0001-7166-5534"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Haibin Wu","raw_affiliation_strings":["National Taiwan University,USA"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,USA","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058219648","display_name":"Ali Aroudi","orcid":"https://orcid.org/0000-0001-5770-0858"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Aroudi","raw_affiliation_strings":["Meta Reality Labs Research,USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Meta Reality Labs Research,USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687379","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0000-0002-3502-1595"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["Meta Reality Labs Research,USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056969511","display_name":"Francesco Nesta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francesco Nesta","raw_affiliation_strings":["Meta Reality Labs Research,USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066528816","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-9621-9888"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Meta Reality Labs Research,USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594372","display_name":"Alexander Reich","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Reich","raw_affiliation_strings":["Meta Reality Labs Research,USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075227645","display_name":"Ke Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Tan","raw_affiliation_strings":["Meta Reality Labs Research,USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101474128"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.561,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78279031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9936000108718872,"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":0.9936000108718872,"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/speech-enhancement","display_name":"Speech enhancement","score":0.7213331460952759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5909267663955688},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47881561517715454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18813002109527588},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09758606553077698}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7213331460952759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5909267663955688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47881561517715454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18813002109527588},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09758606553077698}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2603567530","https://openalex.org/W2696558042","https://openalex.org/W2805233667","https://openalex.org/W2889442120","https://openalex.org/W2891607145","https://openalex.org/W2892110446","https://openalex.org/W2952218014","https://openalex.org/W2962998773","https://openalex.org/W2963045393","https://openalex.org/W2998161426","https://openalex.org/W3035321581","https://openalex.org/W3097906045","https://openalex.org/W3097934054","https://openalex.org/W3097945073","https://openalex.org/W3197912330","https://openalex.org/W4225302959","https://openalex.org/W4297841766","https://openalex.org/W6677258307","https://openalex.org/W6762114000"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"MetricGAN,":[0],"a":[1],"notable":[2],"generative":[3],"approach,":[4],"provides":[5],"an":[6],"effective":[7],"framework":[8],"to":[9,14,79,105,123],"train":[10],"speech":[11,129],"enhancement":[12],"models":[13,48,55,71,122],"produce":[15,56],"high":[16,41],"metric":[17],"scores.":[18],"However,":[19],"we":[20,44,66,98],"identify":[21],"two":[22,102],"key":[23],"limitations":[24],"of":[25],"current":[26],"MetricGAN-family":[27],"models,":[28],"i.e.":[29],"neglecting":[30],"certain":[31],"mainstream":[32,50],"metrics":[33],"during":[34],"evaluation":[35,38],"and":[36,59,91,100,111],"conducting":[37],"exclusively":[39],"at":[40,72],"SNR.":[42],"Firstly,":[43],"comprehensively":[45],"assess":[46],"MetricGAN":[47,54,70,121],"using":[49],"metrics,":[51],"surprisingly":[52],"revealing":[53],"worse":[57],"SISDR":[58,90,109],"STOI":[60,92],"than":[61],"unprocessed":[62],"noisy":[63],"speech.":[64],"Secondly,":[65],"demonstrate":[67],"that":[68,116],"training":[69,103],"low":[73],"SNR":[74],"often":[75],"results":[76],"in":[77],"convergence":[78],"biased":[80],"local":[81,125],"minima,":[82,126],"where":[83],"PESQ":[84],"scores":[85],"are":[86],"inflated":[87],"while":[88],"their":[89],"values":[93],"deteriorate":[94],"significantly.":[95],"In":[96],"addition,":[97],"propose":[99],"validate":[101],"tricks":[104,118],"address":[106],"these":[107,117],"issues:":[108],"regularization":[110],"mixture-of-actor":[112],"training.":[113],"We":[114],"find":[115],"effectively":[119],"guide":[120],"avoid":[124],"thus":[127],"improving":[128],"quality.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}