{"id":"https://openalex.org/W2991361823","doi":"https://doi.org/10.1109/taslp.2019.2955276","title":"Learning Complex Spectral Mapping With Gated Convolutional Recurrent Networks for Monaural Speech Enhancement","display_name":"Learning Complex Spectral Mapping With Gated Convolutional Recurrent Networks for Monaural Speech Enhancement","publication_year":2019,"publication_date":"2019-11-22","ids":{"openalex":"https://openalex.org/W2991361823","doi":"https://doi.org/10.1109/taslp.2019.2955276","mag":"2991361823","pmid":"https://pubmed.ncbi.nlm.nih.gov/33748323","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/7970735"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2955276","doi":"https://doi.org/10.1109/taslp.2019.2955276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2955276","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,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7970735","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058209019","display_name":"Ke Tan","orcid":"https://orcid.org/0000-0001-5073-8060","observed_orcids":["https://orcid.org/0000-0001-5073-8060"]},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Tan","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, 43210-1277 USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, USA"],"raw_orcid":"https://orcid.org/0000-0001-5073-8060","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, 43210-1277 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319","observed_orcids":["https://orcid.org/0000-0001-8195-6319"]},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43210-1277, USA","Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43210-1277, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":20.1807,"has_fulltext":false,"cited_by_count":350,"citation_normalized_percentile":{"value":0.99630996,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"380","last_page":"390"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":9.999999747378752e-05,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.0,"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/monaural-speech-enhancement","display_name":"monaural speech enhancement","score":0.9769999980926514},{"id":"https://openalex.org/keywords/phase-estimation","display_name":"phase estimation","score":0.8700000047683716},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.8130000233650208},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.625},{"id":"https://openalex.org/keywords/speech-quality","display_name":"speech quality","score":0.6850000023841858}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8104680776596069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095943093299866},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7048519849777222},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6894546747207642},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.6603304743766785},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6524872779846191},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5893916487693787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4673728346824646},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.456339031457901},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41847991943359375},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14360857009887695},{"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":3,"locations":[{"id":"doi:10.1109/taslp.2019.2955276","doi":"https://doi.org/10.1109/taslp.2019.2955276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2955276","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,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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"},{"id":"pmid:33748323","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33748323","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"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"},{"id":"pmh:oai:pubmedcentral.nih.gov:7970735","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7970735","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:7970735","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7970735","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G6572069668","display_name":"Speech segregation to improve intelligility of reverberant-noisy speech","funder_award_id":"R01DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G8122156136","display_name":"Improving intelligibility in noise for hearing-impaired listeners","funder_award_id":"R01DC015521","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1516630152","https://openalex.org/W1536373746","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W1897240248","https://openalex.org/W1942758450","https://openalex.org/W1974387177","https://openalex.org/W2011853193","https://openalex.org/W2024490156","https://openalex.org/W2031647436","https://openalex.org/W2041498927","https://openalex.org/W2046869671","https://openalex.org/W2048142341","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2078528584","https://openalex.org/W2094461119","https://openalex.org/W2141998673","https://openalex.org/W2144786298","https://openalex.org/W2156387975","https://openalex.org/W2176412452","https://openalex.org/W2291877678","https://openalex.org/W2405774341","https://openalex.org/W2516342150","https://openalex.org/W2526733715","https://openalex.org/W2561557072","https://openalex.org/W2567070169","https://openalex.org/W2605138598","https://openalex.org/W2678916739","https://openalex.org/W2753709519","https://openalex.org/W2771725120","https://openalex.org/W2774389566","https://openalex.org/W2785523195","https://openalex.org/W2789131247","https://openalex.org/W2803417661","https://openalex.org/W2889286744","https://openalex.org/W2889442120","https://openalex.org/W2897371647","https://openalex.org/W2940275453","https://openalex.org/W2963045393","https://openalex.org/W2963636093","https://openalex.org/W2963751183","https://openalex.org/W2963970792"],"related_works":["https://openalex.org/W2940275453","https://openalex.org/W4386920618","https://openalex.org/W3156857934","https://openalex.org/W4318185059","https://openalex.org/W4415917335","https://openalex.org/W4375864825","https://openalex.org/W2774389566","https://openalex.org/W4200292474","https://openalex.org/W3096408984","https://openalex.org/W4391021527"],"abstract_inverted_index":{"Phase":[0],"is":[1],"important":[2],"for":[3,69,79,99],"perceptual":[4],"quality":[5],"of":[6,24,40,45,55,105],"speech.":[7,56],"However,":[8],"it":[9],"seems":[10],"intractable":[11],"to":[12,21,33,75],"directly":[13],"estimate":[14,34],"phase":[15,53,144],"spectra":[16],"through":[17],"supervised":[18],"learning":[19],"due":[20],"their":[22],"lack":[23],"spectrotemporal":[25],"structure":[26],"in":[27,103],"it.":[28],"Complex":[29],"spectral":[30,71,101,124,135],"mapping":[31,102,125,136],"aims":[32],"the":[35,88,113,138],"real":[36],"and":[37,52,110,120,126],"imaginary":[38],"spectrograms":[39],"clean":[41],"speech":[42,81,108],"from":[43],"those":[44],"noisy":[46],"speech,":[47],"which":[48,73],"simultaneously":[49],"enhances":[50],"magnitude":[51,123],"responses":[54],"Inspired":[57],"by":[58],"multi-task":[59],"learning,":[60],"we":[61],"propose":[62],"a":[63,76],"gated":[64],"convolutional":[65,95],"recurrent":[66],"network":[67,97],"(GCRN)":[68],"complex":[70,100,127,134],"mapping,":[72],"amounts":[74],"causal":[77],"system":[78],"monaural":[80],"enhancement.":[82],"Our":[83],"experimental":[84],"results":[85],"suggest":[86],"that":[87,133],"proposed":[89,114,139],"GCRN":[90,140],"substantially":[91],"outperforms":[92],"an":[93,142],"existing":[94],"neural":[96],"(CNN)":[98],"terms":[104],"both":[106],"objective":[107],"intelligibility":[109],"quality.":[111],"Moreover,":[112],"approach":[115],"yields":[116],"significantly":[117],"higher":[118],"STOI":[119],"PESQ":[121],"than":[122],"ratio":[128],"masking.":[129],"We":[130],"also":[131],"find":[132],"with":[137],"provides":[141],"effective":[143],"estimate.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":28},{"year":2025,"cited_by_count":57},{"year":2024,"cited_by_count":65},{"year":2023,"cited_by_count":72},{"year":2022,"cited_by_count":58},{"year":2021,"cited_by_count":58},{"year":2020,"cited_by_count":12}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2019-12-05T00:00:00"}