{"id":"https://openalex.org/W3201199308","doi":"https://doi.org/10.1109/taslp.2021.3111566","title":"Multi-Metric Optimization Using Generative Adversarial Networks for Near-End Speech Intelligibility Enhancement","display_name":"Multi-Metric Optimization Using Generative Adversarial Networks for Near-End Speech Intelligibility Enhancement","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3201199308","doi":"https://doi.org/10.1109/taslp.2021.3111566","mag":"3201199308"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3111566","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3111566","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09536406.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09536406.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103123052","display_name":"Haoyu Li","orcid":"https://orcid.org/0000-0001-9058-633X"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haoyu Li","raw_affiliation_strings":["Department of Informatics, National Institute of Informatics, 13513 Chiyoda-ku, Japan, 101-8430 (e-mail: haoyuli@nii.ac.jp)","National Institute of Informat-ics, and with the Department of Informatics, SOKENDAI, Tokyo 101-8340, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9058-633X","affiliations":[{"raw_affiliation_string":"Department of Informatics, National Institute of Informatics, 13513 Chiyoda-ku, Japan, 101-8430 (e-mail: haoyuli@nii.ac.jp)","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informat-ics, and with the Department of Informatics, SOKENDAI, Tokyo 101-8340, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, 13513 Chiyoda-ku Tokyo, Japan, 101-8430 (e-mail: jyamagis@nii.ac.jp)","National Institute of Informat-ics, and with the Department of Informatics, SOKENDAI, Tokyo 101-8340, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2752-3955","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, 13513 Chiyoda-ku Tokyo, Japan, 101-8430 (e-mail: jyamagis@nii.ac.jp)","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informat-ics, and with the Department of Informatics, SOKENDAI, Tokyo 101-8340, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6469,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84402586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"3000","last_page":"3011"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9995999932289124,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8129285573959351},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7518713474273682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6948343515396118},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6050308346748352},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5042017698287964},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5006728172302246},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49194762110710144},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4467943012714386},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4307194948196411},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4279826283454895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3606574833393097},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17806991934776306},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1346796452999115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129285573959351},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7518713474273682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6948343515396118},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6050308346748352},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5042017698287964},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5006728172302246},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49194762110710144},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4467943012714386},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4307194948196411},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4279826283454895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3606574833393097},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17806991934776306},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1346796452999115},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3111566","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3111566","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09536406.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2021.3111566","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3111566","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09536406.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1526460031","display_name":null,"funder_award_id":"18H04112","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G1601555150","display_name":"Encoder Factorization for Capturing Dialect and Articulation Level in End-to-End Speech Synthesis","funder_award_id":"19K24372","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1710514051","display_name":null,"funder_award_id":"17H04687","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G3582502417","display_name":null,"funder_award_id":"JPMJCR18A6","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G360976672","display_name":"Biometric Information Protection Utilization Infrastructure to Ensure Personal Convenience and Prevent Identity Theft","funder_award_id":"18H04120","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4104777191","display_name":null,"funder_award_id":"16H06302","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G5216536157","display_name":null,"funder_award_id":"18H04120","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G5375717198","display_name":null,"funder_award_id":"18KT0051","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G6299358200","display_name":"PRISM: Speech privacy preservation based on selecting masking","funder_award_id":"18H04112","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6954941931","display_name":"Communication System for Defending against Attacks of Media Clones","funder_award_id":"16H06302","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7623259429","display_name":"Robust voice cloning technologies in noisy environments and its applications","funder_award_id":"17H04687","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7879866177","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G8315410620","display_name":null,"funder_award_id":"JPMJCR18A6","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G8937069383","display_name":"Safe and secure speech information processing based on liveness detection and ASVspoof challenge","funder_award_id":"18KT0051","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3201199308.pdf","grobid_xml":"https://content.openalex.org/works/W3201199308.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W65497148","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1659842140","https://openalex.org/W1799366690","https://openalex.org/W1921523184","https://openalex.org/W1991906437","https://openalex.org/W1996304098","https://openalex.org/W2044893557","https://openalex.org/W2050758723","https://openalex.org/W2058542017","https://openalex.org/W2075076415","https://openalex.org/W2082668798","https://openalex.org/W2092644348","https://openalex.org/W2104387086","https://openalex.org/W2121973264","https://openalex.org/W2128631678","https://openalex.org/W2128653836","https://openalex.org/W2136682440","https://openalex.org/W2146324387","https://openalex.org/W2296704011","https://openalex.org/W2395675680","https://openalex.org/W2403011125","https://openalex.org/W2404548911","https://openalex.org/W2516001803","https://openalex.org/W2611963065","https://openalex.org/W2623662528","https://openalex.org/W2747057337","https://openalex.org/W2749552851","https://openalex.org/W2750452568","https://openalex.org/W2763767706","https://openalex.org/W2767488834","https://openalex.org/W2785678896","https://openalex.org/W2912191105","https://openalex.org/W2937484199","https://openalex.org/W2943895317","https://openalex.org/W2952218014","https://openalex.org/W2956105671","https://openalex.org/W2963045393","https://openalex.org/W2963454081","https://openalex.org/W2963836885","https://openalex.org/W2964121744","https://openalex.org/W2972497784","https://openalex.org/W2973133192","https://openalex.org/W2981493186","https://openalex.org/W3016050488","https://openalex.org/W3032727804","https://openalex.org/W3033411150","https://openalex.org/W3037038648","https://openalex.org/W3096795913","https://openalex.org/W3096949857","https://openalex.org/W3103318788","https://openalex.org/W3103840368","https://openalex.org/W3130016944","https://openalex.org/W4231807801","https://openalex.org/W4234195863","https://openalex.org/W6631190155","https://openalex.org/W6638444622","https://openalex.org/W6640185926","https://openalex.org/W6697285287","https://openalex.org/W6744720620","https://openalex.org/W6748582592","https://openalex.org/W6758407994","https://openalex.org/W6764637016","https://openalex.org/W6766395181","https://openalex.org/W6778823374"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2085637247","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"The":[0],"intelligibility":[1,33],"of":[2,9,79],"speech":[3,28,72,76,99,134],"severely":[4],"degrades":[5],"in":[6,109,112,122],"the":[7,27,35,47,69,75,148],"presence":[8],"environmental":[10],"noise":[11],"and":[12,42,104,114,142,159],"reverberation.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17,52,86],"propose":[18],"a":[19,82,88],"novel":[20],"deep":[21,89],"learning":[22],"based":[23],"system":[24,117,150],"for":[25,125],"modifying":[26],"signal":[29,39],"to":[30,58,68,73,94],"increase":[31],"its":[32],"under":[34,156],"equal-power":[36],"constraint,":[37],"i.e.,":[38],"power":[40],"before":[41],"after":[43],"modification":[44],"must":[45],"be":[46],"same.":[48],"To":[49],"achieve":[50],"this,":[51],"use":[53],"generative":[54],"adversarial":[55],"networks":[56],"(GANs)":[57],"obtain":[59],"time-frequency":[60],"dependent":[61],"amplification":[62],"factors,":[63],"which":[64,107],"are":[65],"then":[66],"applied":[67],"input":[70],"raw":[71],"reallocate":[74],"energy.":[77],"Instead":[78],"optimizing":[80],"only":[81,120],"single,":[83],"simple":[84],"metric,":[85],"train":[87],"neural":[90],"network":[91],"(DNN)":[92],"model":[93],"simultaneously":[95],"optimize":[96],"multiple":[97],"advanced":[98],"metrics,":[100],"including":[101],"both":[102,139],"intelligibility-":[103],"quality-related":[105],"ones,":[106],"results":[108,137],"notable":[110],"improvements":[111],"performance":[113],"robustness.":[115],"Our":[116],"can":[118],"not":[119],"work":[121],"non-real-time":[123],"mode":[124],"offline":[126],"audio":[127],"playback":[128],"but":[129],"also":[130],"support":[131],"practical":[132],"real-time":[133],"applications.":[135],"Experimental":[136],"using":[138],"objective":[140],"measurements":[141],"subjective":[143],"listening":[144,161],"tests":[145],"indicate":[146],"that":[147],"proposed":[149],"significantly":[151],"outperforms":[152],"state-of-the-art":[153],"baseline":[154],"systems":[155],"various":[157],"noisy":[158],"reverberant":[160],"conditions.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}