{"id":"https://openalex.org/W3023846453","doi":"https://doi.org/10.1109/taslp.2020.2991537","title":"A Joint Framework of Denoising Autoencoder and Generative Vocoder for Monaural Speech Enhancement","display_name":"A Joint Framework of Denoising Autoencoder and Generative Vocoder for Monaural Speech Enhancement","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3023846453","doi":"https://doi.org/10.1109/taslp.2020.2991537","mag":"3023846453"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2991537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2991537","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Du","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-3509-9322","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0002-0406-1105","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-4297-4300","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3064,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.88371845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"1493","last_page":"1505"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9962000250816345,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7425232529640198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7104917764663696},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7062011361122131},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6847179532051086},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6502395272254944},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5776242613792419},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5502948760986328},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5321224331855774},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4541648030281067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44911208748817444},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4237288236618042},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.34632495045661926},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.09146058559417725},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07576310634613037}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7425232529640198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7104917764663696},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7062011361122131},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6847179532051086},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6502395272254944},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5776242613792419},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5502948760986328},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5321224331855774},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4541648030281067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44911208748817444},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4237288236618042},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34632495045661926},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.09146058559417725},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07576310634613037},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.2991537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2991537","pdf_url":null,"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":null,"license_id":null,"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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2915035755","display_name":null,"funder_award_id":"2017YFB1002102","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4159508535","display_name":null,"funder_award_id":"U1736210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4224372749","display_name":null,"funder_award_id":"61876214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W190004713","https://openalex.org/W1482149378","https://openalex.org/W1498436455","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W1974387177","https://openalex.org/W1983108229","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2078528584","https://openalex.org/W2120847449","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2156387975","https://openalex.org/W2159202424","https://openalex.org/W2291877678","https://openalex.org/W2406737436","https://openalex.org/W2519091744","https://openalex.org/W2609317876","https://openalex.org/W2619368999","https://openalex.org/W2889286744","https://openalex.org/W2889442120","https://openalex.org/W2892356933","https://openalex.org/W2940275453","https://openalex.org/W2962695743","https://openalex.org/W2962866211","https://openalex.org/W2962882868","https://openalex.org/W2963090522","https://openalex.org/W2963103134","https://openalex.org/W2963300588","https://openalex.org/W2963341071","https://openalex.org/W2963712897","https://openalex.org/W2963782041","https://openalex.org/W2963828919","https://openalex.org/W2963840672","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2972324550","https://openalex.org/W4289305009","https://openalex.org/W4289761690","https://openalex.org/W4294619240","https://openalex.org/W4297798428","https://openalex.org/W6610566761","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6682889407","https://openalex.org/W6696085341","https://openalex.org/W6714644935","https://openalex.org/W6752910514","https://openalex.org/W6756159577","https://openalex.org/W6765987481","https://openalex.org/W6843673214","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2100772705","https://openalex.org/W1986772939","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Conventional":[0],"monaural":[1,95],"speech":[2,12,28,96,102,147,168],"enhancement":[3],"methods":[4],"usually":[5],"enhance":[6,123],"the":[7,15,41,64,100,108,119,124,132,146,150,163],"magnitude":[8,42,65],"spectrum":[9,66,127,136],"of":[10,70,128],"noisy":[11,129],"and":[13,30,43,50,55,82,153,170],"leave":[14],"phase":[16,22,44],"unchanged.":[17],"Recent":[18],"studies":[19],"suggest":[20],"that":[21,162],"is":[23,104,116,137],"also":[24],"important":[25],"for":[26,94,182],"both":[27],"intelligibility":[29,169],"perceptual":[31,171],"quality.":[32,172],"Although":[33],"deep":[34,84,141],"learning":[35],"exhibits":[36],"great":[37],"potential":[38],"on":[39],"enhancing":[40],"spectra":[45],"in":[46,73,98],"complex":[47,53],"spectrogram":[48,54],"domain":[49],"waveform":[51,56,103],"domain,":[52],"are":[57,87,156],"always":[58],"more":[59],"difficult":[60],"to":[61,68,89,122,139,144],"predict":[62],"than":[63,185],"due":[67],"lack":[69],"clear":[71],"structure":[72],"them.":[74],"In":[75],"this":[76],"study,":[77],"a":[78,83,91,111,140],"Mel-domain":[79],"denoising":[80,120,151],"autoencoder":[81,121,152],"generative":[85,142,154],"vocoder":[86,143,155],"stacked":[88],"form":[90],"joint":[92],"framework":[93],"enhancement,":[97],"which":[99],"clean":[101],"reconstructed":[105],"without":[106],"using":[107],"phase.":[109],"Specifically,":[110],"convolutional":[112],"recurrent":[113],"network":[114],"(CRN)":[115],"employed":[117],"as":[118],"Mel":[125,134],"power":[126,135],"speech.":[130],"Then,":[131],"enhanced":[133],"fed":[138],"synthesize":[145],"waveform.":[148],"Furthermore,":[149],"jointly":[157],"fine-tuned.":[158],"Experimental":[159],"results":[160],"show":[161],"proposed":[164],"method":[165,176],"significantly":[166],"improves":[167],"More":[173],"importantly,":[174],"our":[175],"achieves":[177],"much":[178],"better":[179],"generalization":[180],"ability":[181],"untrained":[183],"noises":[184],"previous":[186],"methods.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}