{"id":"https://openalex.org/W3096008106","doi":"https://doi.org/10.21437/interspeech.2020-1169","title":"On Loss Functions and Recurrency Training for GAN-Based Speech Enhancement Systems","display_name":"On Loss Functions and Recurrency Training for GAN-Based Speech Enhancement Systems","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096008106","doi":"https://doi.org/10.21437/interspeech.2020-1169","mag":"3096008106"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1169","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1169","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/A5078783442","display_name":"Zhuohuang Zhang","orcid":"https://orcid.org/0000-0003-3342-323X"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhuohuang Zhang","raw_affiliation_strings":["Department of Computer Science, Indiana University, USA","Department of Speech, Language and Hearing Sciences, Indiana University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Indiana University, USA","institution_ids":["https://openalex.org/I592451"]},{"raw_affiliation_string":"Department of Speech, Language and Hearing Sciences, Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086408501","display_name":"Chengyun Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyun Deng","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064257362","display_name":"Yi Shen","orcid":"https://orcid.org/0000-0003-0063-1200"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Shen","raw_affiliation_strings":["Department of Speech, Language and Hearing Sciences, Indiana University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Speech, Language and Hearing Sciences, Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054209447","display_name":"Donald S. Williamson","orcid":"https://orcid.org/0000-0002-7997-5403"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald S. Williamson","raw_affiliation_strings":["Didi Chuxing, Beijing, China","Department of Computer Science, Indiana University, USA"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]},{"raw_affiliation_string":"Department of Computer Science, Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086086079","display_name":"Yongtao Sha","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongtao Sha","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388333","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0003-4299-1511"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061863093","display_name":"Hui Song","orcid":"https://orcid.org/0000-0002-0458-5136"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Song","raw_affiliation_strings":["Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangang Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5078783442"],"corresponding_institution_ids":["https://openalex.org/I592451"],"apc_list":null,"apc_paid":null,"fwci":4.546,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.9564187,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3266","last_page":"3270"},"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":0.9995999932289124,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/training","display_name":"Training (meteorology)","score":0.6398134231567383},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5592890977859497},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5561389923095703},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3784310519695282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20670273900032043},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10422554612159729}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6398134231567383},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5592890977859497},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5561389923095703},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3784310519695282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20670273900032043},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10422554612159729},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1169","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1169","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":[{"display_name":"Peace, Justice and strong institutions","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W1897240248","https://openalex.org/W1983108229","https://openalex.org/W2042407743","https://openalex.org/W2046869671","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2079735306","https://openalex.org/W2094721231","https://openalex.org/W2144404214","https://openalex.org/W2167204516","https://openalex.org/W2592921646","https://openalex.org/W2603567530","https://openalex.org/W2802304149","https://openalex.org/W2889442120","https://openalex.org/W2891607145","https://openalex.org/W2892129657","https://openalex.org/W2938174197","https://openalex.org/W2939497224","https://openalex.org/W2940177920","https://openalex.org/W2949558265","https://openalex.org/W2963285578","https://openalex.org/W2963341071","https://openalex.org/W2963351212","https://openalex.org/W2964121592","https://openalex.org/W2972802573","https://openalex.org/W2981253098","https://openalex.org/W3015917873","https://openalex.org/W4295521014","https://openalex.org/W4320013936","https://openalex.org/W4394670483"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Recent":[0],"work":[1],"has":[2],"shown":[3],"that":[4,81,116],"it":[5,97],"is":[6],"feasible":[7],"to":[8,24,63,67],"use":[9],"generative":[10],"adversarial":[11],"networks":[12],"(GANs)":[13],"for":[14,36,56,110],"speech":[15,57,111],"enhancement,":[16],"however,":[17],"these":[18],"approaches":[19,135],"have":[20,33,41],"not":[21,42],"been":[22,34,43],"compared":[23],"state-of-the-art":[25],"(SOTA)":[26],"non":[27],"GAN-based":[28,37,69,89],"approaches.Additionally,":[29],"many":[30,137],"loss":[31,59,94,121],"functions":[32,60,95],"proposed":[35,83],"approaches,":[38],"but":[39],"they":[40],"adequately":[44],"compared.In":[45],"this":[46],"study,":[47],"we":[48],"propose":[49],"novel":[50],"convolutional":[51],"recurrent":[52,74],"GAN":[53,109],"(CRGAN)":[54],"architectures":[55],"enhancement.Multiple":[58],"are":[61,76],"adopted":[62],"enable":[64],"direct":[65],"comparisons":[66],"other":[68,99],"systems.The":[70],"benefits":[71,105],"of":[72,106],"including":[73],"layers":[75],"also":[77],"explored.Our":[78],"results":[79],"show":[80],"the":[82,87,92,104,113,124,130],"CRGAN":[84,114],"model":[85,115],"outperforms":[86,98],"SOTA":[88],"models":[90],"using":[91,107],"same":[93],"and":[96],"non-GAN":[100],"based":[101],"systems,":[102],"indicating":[103],"a":[108],"enhancement.Overall,":[112],"combines":[117],"an":[118],"objective":[119],"metric":[120],"function":[122],"with":[123],"mean":[125],"squared":[126],"error":[127],"(MSE)":[128],"provides":[129],"best":[131],"performance":[132],"over":[133],"comparison":[134],"across":[136],"evaluation":[138],"metrics.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}