{"id":"https://openalex.org/W2921144622","doi":"https://doi.org/10.23919/apsipa.2018.8659692","title":"Time-Frequency Mask-based Speech Enhancement using Convolutional Generative Adversarial Network","display_name":"Time-Frequency Mask-based Speech Enhancement using Convolutional Generative Adversarial Network","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921144622","doi":"https://doi.org/10.23919/apsipa.2018.8659692","mag":"2921144622"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659692","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5101799872","display_name":"Neil Shah","orcid":"https://orcid.org/0000-0003-3261-8430"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Neil Shah","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003062385","display_name":"Meet Soni","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani Institute of Information and Communication Technology","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Meet H. Soni","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101799872"],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":3.3029,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.93502619,"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":"1246","last_page":"1251"},"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":0.9959999918937683,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7797186374664307},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7289680242538452},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5993037819862366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5699316263198853},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5316904783248901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5257257223129272},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.519520103931427},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4956866502761841},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4291130304336548},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39600133895874023},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27830931544303894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797186374664307},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7289680242538452},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5993037819862366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5699316263198853},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5316904783248901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5257257223129272},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.519520103931427},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4956866502761841},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4291130304336548},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39600133895874023},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27830931544303894},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659692","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1516630152","https://openalex.org/W1522301498","https://openalex.org/W1553004968","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W1897240248","https://openalex.org/W1983108229","https://openalex.org/W1995536493","https://openalex.org/W1995562189","https://openalex.org/W1999736059","https://openalex.org/W2035576074","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2094721231","https://openalex.org/W2099471712","https://openalex.org/W2128653836","https://openalex.org/W2141411743","https://openalex.org/W2144404214","https://openalex.org/W2173520492","https://openalex.org/W2193413348","https://openalex.org/W2364134690","https://openalex.org/W2520164769","https://openalex.org/W2603567530","https://openalex.org/W2746457594","https://openalex.org/W2746654391","https://openalex.org/W2747744257","https://openalex.org/W2749588430","https://openalex.org/W2750153721","https://openalex.org/W2949117887","https://openalex.org/W2962896155","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2963420272","https://openalex.org/W2963453742","https://openalex.org/W2963684088","https://openalex.org/W2963971656","https://openalex.org/W2964046669","https://openalex.org/W2964121744","https://openalex.org/W4253928870","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6649113906","https://openalex.org/W6668037159","https://openalex.org/W6685352114","https://openalex.org/W6687566353","https://openalex.org/W6726381175","https://openalex.org/W6742802039","https://openalex.org/W6742907675"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2078761926","https://openalex.org/W2110441383","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":{"Speech":[0],"Enhancement":[1],"(SE)":[2],"system":[3],"deals":[4],"with":[5],"improving":[6],"the":[7,12,16,25,38,43,48,52,88,94,104,119,126,143,147,151,154,160,165],"perceptual":[8],"quality":[9],"and":[10,51,131,146],"preserving":[11],"speech":[13,155,161],"intelligibility":[14],"of":[15,87,141],"noisy":[17,166],"mixture.":[18,167],"The":[19,136],"Time-Frequency":[20],"(T-F)":[21],"masking-based":[22],"SE":[23,40,123],"using":[24],"supervised":[26,107],"learning":[27,61],"algorithm,":[28],"such":[29],"as":[30],"a":[31,70,132],"Deep":[32],"Neural":[33,72],"Network":[34,73,77],"(DNN),":[35],"has":[36],"outperformed":[37],"traditional":[39],"techniques.":[41],"However,":[42],"notable":[44],"difference":[45],"observed":[46,163],"between":[47],"oracle":[49],"mask":[50,81,109,145],"predicted":[53,144],"mask,":[54],"motivates":[55],"us":[56],"to":[57,68,93],"explore":[58],"different":[59],"deep":[60],"architectures.":[62,100],"In":[63],"this":[64],"paper,":[65],"we":[66],"propose":[67],"use":[69],"Convolutional":[71],"(CNN)-based":[74],"Generative":[75],"Adversarial":[76],"(GAN)":[78],"for":[79,106,111],"inherent":[80],"estimation.":[82],"GAN":[83],"takes":[84],"an":[85,91],"advantage":[86],"adversarial":[89],"optimization,":[90],"alternative":[92],"other":[95],"Maximum":[96],"Likelihood":[97],"(ML)":[98],"optimization-based":[99],"We":[101],"also":[102],"show":[103],"need":[105],"T-F":[108,121],"estimation":[110],"effective":[112],"noise":[113],"suppression.":[114],"Experimental":[115],"results":[116],"demonstrate":[117],"that":[118],"proposed":[120,128],"mask-based":[122],"significantly":[124],"outperforms":[125],"recently":[127],"end-to-end":[129],"SEGAN":[130],"GAN-based":[133],"Pix2Pix":[134],"architecture.":[135],"performance":[137],"evaluation":[138],"in":[139,153,164],"terms":[140],"both":[142],"objective":[148],"measures,":[149],"dictates":[150],"improvement":[152],"quality,":[156],"while":[157],"simultaneously":[158],"reducing":[159],"distortion":[162]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}