{"id":"https://openalex.org/W2802304149","doi":"https://doi.org/10.1109/icassp.2018.8462068","title":"Time-Frequency Masking-Based Speech Enhancement Using Generative Adversarial Network","display_name":"Time-Frequency Masking-Based Speech Enhancement Using Generative Adversarial Network","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2802304149","doi":"https://doi.org/10.1109/icassp.2018.8462068","mag":"2802304149"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5003062385","display_name":"Meet Soni","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","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":["Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","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 University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neil Shah","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113880393","display_name":"Hemant A. Patil","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","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":["Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":21.4677,"has_fulltext":false,"cited_by_count":219,"citation_normalized_percentile":{"value":0.99679364,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5039","last_page":"5043"},"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":0.9973999857902527,"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/T11309","display_name":"Music and Audio Processing","score":0.9958999752998352,"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/speech-enhancement","display_name":"Speech enhancement","score":0.8332604765892029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7959245443344116},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.7594146728515625},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5750895738601685},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.525469183921814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4433871805667877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43829068541526794},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43698850274086},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38373759388923645},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.30286529660224915},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11353060603141785}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8332604765892029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7959245443344116},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7594146728515625},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5750895738601685},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.525469183921814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4433871805667877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43829068541526794},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43698850274086},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38373759388923645},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.30286529660224915},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11353060603141785},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W190004713","https://openalex.org/W1516630152","https://openalex.org/W1522301498","https://openalex.org/W1897240248","https://openalex.org/W1983108229","https://openalex.org/W1995536493","https://openalex.org/W1999736059","https://openalex.org/W2042407743","https://openalex.org/W2053165762","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2094721231","https://openalex.org/W2141411743","https://openalex.org/W2144404214","https://openalex.org/W2364134690","https://openalex.org/W2603567530","https://openalex.org/W2746457594","https://openalex.org/W2746654391","https://openalex.org/W2747744257","https://openalex.org/W2962896155","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2963420272","https://openalex.org/W4253928870","https://openalex.org/W4320013936","https://openalex.org/W6630966923","https://openalex.org/W6650282889","https://openalex.org/W6664102729","https://openalex.org/W6667372801","https://openalex.org/W6680858114"],"related_works":["https://openalex.org/W3081694532","https://openalex.org/W2102148524","https://openalex.org/W2092272653","https://openalex.org/W1980230116","https://openalex.org/W2314720829","https://openalex.org/W4387002515","https://openalex.org/W1517958729","https://openalex.org/W1630865680","https://openalex.org/W2002555665","https://openalex.org/W271627879"],"abstract_inverted_index":{"The":[0,20,136,158],"success":[1],"of":[2,12,45,50,106,123,139,187],"time-frequency":[3],"(T-F)":[4],"mask-based":[5],"approaches":[6],"is":[7],"dependent":[8],"on":[9],"the":[10,16,69,80,92,97,104,111,121,140,144,147,153,192],"accuracy":[11],"predicted":[13,129],"mask":[14,93,113,149],"given":[15],"noisy":[17,193],"spectral":[18],"features.":[19],"state-of-the-art":[21,154],"methods":[22],"in":[23,62,75,109,146,170,191],"T-":[24],"F":[25],"masking-based":[26,64],"enhancement":[27,65,168],"employ":[28],"Deep":[29],"Neural":[30],"Network":[31],"(DNN)":[32],"to":[33,59,72,133],"predict":[34],"mask.":[35],"Recently,":[36],"Generative":[37],"Adversarial":[38],"Networks":[39],"(GAN)":[40],"are":[41],"gaining":[42],"popularity":[43],"instead":[44],"maximum":[46],"likelihood":[47],"(ML)-based":[48],"optimization":[49,156],"deep":[51],"learning":[52],"architectures.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,86,102],"propose":[58,115],"exploit":[60],"GAN":[61,74,108],"T-F":[63,99],"framework.":[66],"We":[67],"present":[68,190],"viable":[70],"strategy":[71],"use":[73,87,122],"such":[76],"application":[77],"by":[78],"modifying":[79],"existing":[81],"approach.":[82],"To":[83],"achieve":[84],"this,":[85],"a":[88,116,164,176],"method":[89,142],"that":[90],"learns":[91],"implicitly":[94],"while":[95,174],"predicting":[96,110],"clean":[98],"representation.":[100],"Moreover,":[101],"show":[103],"failure":[105],"vanilla":[107],"accurate":[112,148],"and":[114,130,183],"regularized":[117],"objective":[118,137],"function":[119],"with":[120],"Mean":[124],"Square":[125],"Error":[126],"(MSE)":[127],"between":[128,179],"target":[131],"spectrum":[132],"overcome":[134],"it.":[135],"evaluation":[138],"proposed":[141,159],"shows":[143],"improvement":[145],"prediction,":[150],"as":[151],"against":[152],"ML-based":[155],"techniques.":[157],"system":[160,169],"significantly":[161],"improves":[162],"over":[163],"recent":[165],"GAN-based":[166],"speech":[167,172,181],"improving":[171],"quality,":[173],"maintaining":[175],"better":[177],"trade-off":[178],"less":[180],"distortion":[182],"more":[184],"effective":[185],"removal":[186],"background":[188],"interferences":[189],"mixture.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":46},{"year":2020,"cited_by_count":55},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}