{"id":"https://openalex.org/W4224916670","doi":"https://doi.org/10.1109/icassp43922.2022.9747267","title":"Joint Magnitude Estimation and Phase Recovery Using Cycle-In-Cycle GAN for Non-Parallel Speech Enhancement","display_name":"Joint Magnitude Estimation and Phase Recovery Using Cycle-In-Cycle GAN for Non-Parallel Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224916670","doi":"https://doi.org/10.1109/icassp43922.2022.9747267"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747267","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5025635655","display_name":"Guochen Yu","orcid":"https://orcid.org/0000-0002-7179-1044"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guochen Yu","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","institution_ids":["https://openalex.org/I75689368","https://openalex.org/I4391768176"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053757616","display_name":"Andong Li","orcid":"https://orcid.org/0000-0003-4094-8448"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andong Li","raw_affiliation_strings":["Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Acoustics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741273","display_name":"Yutian Wang","orcid":"https://orcid.org/0000-0002-8033-8727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutian Wang","raw_affiliation_strings":["Bytedance,Beijing,China","Bytedance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Bytedance,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Bytedance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016681207","display_name":"Yinuo Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinuo Guo","raw_affiliation_strings":["Bytedance,Beijing,China","Bytedance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Bytedance,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Bytedance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460841","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-8476-888X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Bytedance,Beijing,China","Bytedance, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Bytedance,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Bytedance, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070266277","display_name":"Chengshi Zheng","orcid":"https://orcid.org/0000-0001-5656-994X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengshi Zheng","raw_affiliation_strings":["Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Acoustics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025635655"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069","https://openalex.org/I4391768176","https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":1.3518,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82748815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6967","last_page":"6971"},"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":0.9947999715805054,"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":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.7498164176940918},{"id":"https://openalex.org/keywords/magnitude","display_name":"Magnitude (astronomy)","score":0.7197136282920837},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6301811933517456},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6141526699066162},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6054008603096008},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5671939253807068},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5306925773620605},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5150096416473389},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4484460949897766},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4342082440853119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4118180274963379},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36874616146087646},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2750126123428345},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09002381563186646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498164176940918},{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.7197136282920837},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6301811933517456},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6141526699066162},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6054008603096008},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5671939253807068},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5306925773620605},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5150096416473389},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4484460949897766},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4342082440853119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4118180274963379},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36874616146087646},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2750126123428345},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09002381563186646},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747267","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":0.8299999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1983108229","https://openalex.org/W2044893557","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2094721231","https://openalex.org/W2144404214","https://openalex.org/W2603567530","https://openalex.org/W2802304149","https://openalex.org/W2810518847","https://openalex.org/W2888858245","https://openalex.org/W2889442120","https://openalex.org/W2940177920","https://openalex.org/W2949558265","https://openalex.org/W2962793481","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2963452667","https://openalex.org/W2964121592","https://openalex.org/W2972443522","https://openalex.org/W2991361823","https://openalex.org/W3015411705","https://openalex.org/W3031135612","https://openalex.org/W3088775906","https://openalex.org/W3092000928","https://openalex.org/W3096008106","https://openalex.org/W3096408984","https://openalex.org/W3161273075","https://openalex.org/W3161480375","https://openalex.org/W3162493033","https://openalex.org/W3186301694","https://openalex.org/W3197260772","https://openalex.org/W3200407957","https://openalex.org/W4253928870","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6667372801","https://openalex.org/W6738884980","https://openalex.org/W6751512325","https://openalex.org/W6762114000","https://openalex.org/W6785764544","https://openalex.org/W6798972960"],"related_works":["https://openalex.org/W2376418092","https://openalex.org/W2072983018","https://openalex.org/W1016952678","https://openalex.org/W2257644995","https://openalex.org/W1513444457","https://openalex.org/W4311345787","https://openalex.org/W2188141918","https://openalex.org/W3185336960","https://openalex.org/W2042652790","https://openalex.org/W2118992737"],"abstract_inverted_index":{"For":[0],"the":[1,27,41,47,52,67,93,106,117,124,129,147,154,168],"lack":[2],"of":[3,26,120],"adequate":[4],"paired":[5,172],"noisy-clean":[6],"speech":[7,21,54,187],"corpus":[8],"in":[9,51,182],"many":[10,35],"real":[11],"scenarios,":[12],"non-parallel":[13,162],"training":[14,167],"is":[15,88],"a":[16,80,111,133,137],"promising":[17],"task":[18],"for":[19],"DNN-based":[20],"enhancement":[22],"methods.":[23],"However,":[24],"because":[25],"severe":[28],"mismatch":[29],"between":[30],"input":[31],"and":[32,45,77,79,96,145,186],"target":[33,69],"speeches,":[34],"previous":[36,159],"studies":[37],"only":[38],"focus":[39],"on":[40,166],"magnitude":[42,76,95,112,119],"spectrum":[43,72],"estimation":[44],"remain":[46],"phase":[48,97,143],"unaltered,":[49],"resulting":[50],"degraded":[53],"quality":[55],"under":[56,102,161],"low":[57],"signal-to-noise":[58],"ratio":[59],"conditions.":[60],"To":[61],"tackle":[62],"this":[63],"problem,":[64],"we":[65,109,127],"decouple":[66],"difficult":[68],"w.r.t.":[70],"original":[71],"optimization":[73],"into":[74],"spectral":[75,94,118],"phase,":[78],"novel":[81],"Cycle-in-Cycle":[82],"generative":[83],"adversarial":[84],"network":[85],"(dubbed":[86],"CinCGAN)":[87],"proposed":[89,155],"to":[90,114,140],"jointly":[91],"estimate":[92,116],"information":[98,144],"stage":[99,101],"by":[100],"unpaired":[103],"data.":[104],"In":[105,123],"first":[107],"stage,":[108,126],"pretrain":[110],"Cycle-GAN":[113],"coarsely":[115],"clean":[121],"speech.":[122],"second":[125],"incorporate":[128],"pretrained":[130],"CycleGAN":[131,135],"with":[132,170],"complex-valued":[134],"as":[136],"cycle-in-cycle":[138],"structure":[139],"simultaneously":[141],"recover":[142],"refine":[146],"overall":[148],"spectrum.":[149],"Experimental":[150],"results":[151],"demonstrate":[152],"that":[153,176],"approach":[156],"significantly":[157],"outperforms":[158],"baselines":[160],"training.":[163],"The":[164],"evaluation":[165],"models":[169],"standard":[171],"data":[173],"also":[174],"shows":[175],"CinCGAN":[177],"achieves":[178],"remarkable":[179],"performance":[180],"especially":[181],"reducing":[183],"background":[184],"noise":[185],"distortion.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}