{"id":"https://openalex.org/W4388820618","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317366","title":"Study of Generative Adversarial Networks for Noisy Speech Simulation from Clean Speech","display_name":"Study of Generative Adversarial Networks for Noisy Speech Simulation from Clean Speech","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820618","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317366"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317366","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5024759921","display_name":"Leander Melroy Maben","orcid":null},"institutions":[{"id":"https://openalex.org/I164861460","display_name":"Manipal Academy of Higher Education","ror":"https://ror.org/02xzytt36","country_code":"IN","type":"education","lineage":["https://openalex.org/I164861460"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Leander Melroy Maben","raw_affiliation_strings":["Manipal Institute of Technology,Manipal,India","Manipal Institute of Technology, Manipal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manipal Institute of Technology,Manipal,India","institution_ids":["https://openalex.org/I164861460"]},{"raw_affiliation_string":"Manipal Institute of Technology, Manipal, India","institution_ids":["https://openalex.org/I164861460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041055222","display_name":"Zixun Guo","orcid":"https://orcid.org/0000-0002-7327-4382"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zixun Guo","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418370","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0001-7587-3314"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092005286","display_name":"Utkarsh Chudiwal","orcid":null},"institutions":[{"id":"https://openalex.org/I64295750","display_name":"Indian Institute of Technology Indore","ror":"https://ror.org/01hhf7w52","country_code":"IN","type":"education","lineage":["https://openalex.org/I64295750"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Utkarsh Chudiwal","raw_affiliation_strings":["Indian Institute of Technology,Indore,India","Indian Institute of Technology, Indore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Indore,India","institution_ids":["https://openalex.org/I64295750"]},{"raw_affiliation_string":"Indian Institute of Technology, Indore, India","institution_ids":["https://openalex.org/I64295750"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chng Eng Siong","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chng Eng Siong","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"1143","last_page":"1149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9912999868392944,"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/timit","display_name":"TIMIT","score":0.8375307321548462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7871293425559998},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6969879269599915},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5323463082313538},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5260926485061646},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.44696730375289917},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42779725790023804},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.415425181388855},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"Environmental noise","score":0.41402584314346313},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.36849135160446167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36840546131134033},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11294567584991455},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08324724435806274}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8375307321548462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871293425559998},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6969879269599915},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5323463082313538},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5260926485061646},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44696730375289917},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42779725790023804},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.415425181388855},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.41402584314346313},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.36849135160446167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36840546131134033},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11294567584991455},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08324724435806274},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317366","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1573570773","https://openalex.org/W1831910457","https://openalex.org/W1922655562","https://openalex.org/W2166637769","https://openalex.org/W2311973309","https://openalex.org/W2559655401","https://openalex.org/W2899396049","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963211739","https://openalex.org/W2978074392","https://openalex.org/W3011871163","https://openalex.org/W3012086229","https://openalex.org/W3087443678","https://openalex.org/W3108316907","https://openalex.org/W3162512456","https://openalex.org/W3195797672","https://openalex.org/W3196878101","https://openalex.org/W4212774754","https://openalex.org/W4221156109","https://openalex.org/W4297841623","https://openalex.org/W6604215140","https://openalex.org/W6767111847","https://openalex.org/W6771763809","https://openalex.org/W6803559545"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W2083296885","https://openalex.org/W2015876361","https://openalex.org/W2131486661"],"abstract_inverted_index":{"The":[0],"performance":[1],"of":[2,52,61,97,104,116,139],"speech":[3,9,31,37,40],"processing":[4],"models":[5,33],"trained":[6],"on":[7,136],"clean":[8,39],"drops":[10],"significantly":[11],"in":[12,102,114],"noisy":[13,17,36],"conditions.":[14],"Training":[15],"with":[16],"datasets":[18,25,138],"alleviates":[19],"the":[20,50,65,82,90,124,127],"problem,":[21],"but":[22],"procuring":[23],"such":[24],"is":[26],"not":[27],"always":[28],"feasible.":[29],"Noisy":[30],"simulation":[32],"that":[34],"generate":[35],"from":[38,64],"help":[41],"remedy":[42],"this":[43],"issue.":[44],"In":[45],"our":[46],"work,":[47],"we":[48],"study":[49],"ability":[51],"Generative":[53],"Adversarial":[54],"Networks":[55],"(GANs)":[56],"to":[57,123],"simulate":[58],"a":[59],"variety":[60],"noises.":[62],"Noise":[63],"Ultra-High-Frequency/Very-High-Frequency":[66],"(UHF/VHF),":[67],"additive":[68],"stationary":[69],"and":[70,72,87,89,100,109,112,130],"non-stationary,":[71],"codec":[73],"distortion":[74],"categories":[75],"are":[76],"studied.":[77],"We":[78,94],"propose":[79],"four":[80],"GANs:":[81],"non-parallel":[83],"translators,":[84],"SpeechAttentionGAN,":[85],"SimuGAN,":[86],"MaskCycleGAN-Augment,":[88],"parallel":[91],"translator,":[92],"Speech2Speech-Augment.":[93],"achieved":[95],"improvements":[96],"55.8%,":[98],"28.9%,":[99],"22.8%":[101],"terms":[103,115],"Multi-Scale":[105],"Spectral":[106,118],"Loss":[107],"(MSSL)":[108],"49.3%,":[110],"28.8%,":[111],"18.2%":[113],"Log":[117],"Distance":[119],"(LSD)":[120],"as":[121],"compared":[122],"baseline":[125],"for":[126],"RATS,":[128],"TIMIT-Cabin,":[129],"TIMIT-Helicopter":[131],"datasets,":[132],"respectively,":[133],"after":[134],"training":[135],"small":[137],"about":[140],"3":[141],"minutes.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}