{"id":"https://openalex.org/W3096949857","doi":"https://doi.org/10.21437/interspeech.2020-1016","title":"iMetricGAN: Intelligibility Enhancement for Speech-in-Noise Using Generative Adversarial Network-Based Metric Learning","display_name":"iMetricGAN: Intelligibility Enhancement for Speech-in-Noise Using Generative Adversarial Network-Based Metric Learning","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096949857","doi":"https://doi.org/10.21437/interspeech.2020-1016","mag":"3096949857"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1016","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1016","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":"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/A5100358569","display_name":"Haoyu Li","orcid":"https://orcid.org/0000-0002-7102-8348"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haoyu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szu-Wei Fu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100358569"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5761,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90566162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1336","last_page":"1340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.996399998664856,"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":0.996399998664856,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7547069191932678},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7142096757888794},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6956868171691895},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6486602425575256},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5778673887252808},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5766041278839111},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5569246411323547},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.5416510701179504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39210766553878784},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24220162630081177},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2030440866947174},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08354982733726501}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7547069191932678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7142096757888794},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6956868171691895},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6486602425575256},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5778673887252808},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5766041278839111},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5569246411323547},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.5416510701179504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39210766553878784},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24220162630081177},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2030440866947174},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08354982733726501},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"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:10.21437/interspeech.2020-1016","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1016","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3156763702","https://openalex.org/W3156291593","https://openalex.org/W3198184493","https://openalex.org/W2901368259","https://openalex.org/W2944414373","https://openalex.org/W3202553031","https://openalex.org/W3216956295","https://openalex.org/W2785844714","https://openalex.org/W3208910454","https://openalex.org/W4225712171"],"abstract_inverted_index":{"The":[0],"intelligibility":[1,29,63,88,96,110],"of":[2,43,83],"natural":[3],"speech":[4,22,45,62,87],"is":[5],"seriously":[6],"degraded":[7],"when":[8,112],"exposed":[9],"to":[10,25,59],"adverse":[11],"noisy":[12],"environments.":[13],"In":[14,103],"this":[15],"work,":[16],"we":[17,54],"propose":[18],"a":[19,99],"deep":[20],"learning-based":[21],"modification":[23],"method":[24],"compensate":[26],"for":[27],"the":[28,32,35,44,61,74],"loss,":[30],"with":[31,65],"constraint":[33],"that":[34,73],"root":[36],"mean":[37],"square":[38],"(RMS)":[39],"level":[40],"and":[41,50,92,115],"duration":[42],"signal":[46],"are":[47],"maintained":[48],"before":[49],"after":[51],"modifications.":[52],"Specifically,":[53],"utilize":[55],"an":[56],"iMetricGAN":[57,76],"approach":[58],"optimize":[60],"metrics":[64],"generative":[66],"adversarial":[67],"networks":[68],"(GANs).":[69],"Experimental":[70],"results":[71],"show":[72],"proposed":[75],"outperforms":[77],"conventional":[78],"state-of-the-art":[79],"algorithms":[80],"in":[81,89],"terms":[82],"objective":[84,95],"measures,":[85],"i.e.,":[86],"bits":[90],"(SIIB)":[91],"extended":[93],"short-time":[94],"(ESTOI),":[97],"under":[98],"Cafeteria":[100],"noise":[101,114],"condition.":[102],"addition,":[104],"formal":[105],"listening":[106],"tests":[107],"reveal":[108],"significant":[109],"gains":[111],"both":[113],"reverberation":[116],"exist.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}