{"id":"https://openalex.org/W2940275453","doi":"https://doi.org/10.1109/icassp.2019.8682834","title":"Complex Spectral Mapping with a Convolutional Recurrent Network for Monaural Speech Enhancement","display_name":"Complex Spectral Mapping with a Convolutional Recurrent Network for Monaural Speech Enhancement","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2940275453","doi":"https://doi.org/10.1109/icassp.2019.8682834","mag":"2940275453"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5058209019","display_name":"Ke Tan","orcid":"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, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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"},"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":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, 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":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":172,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6865","last_page":"6869"},"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":0.9976000189781189,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9338865280151367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7242771983146667},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7074883580207825},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6934597492218018},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6208793520927429},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6029799580574036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45457005500793457},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45008060336112976},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43294376134872437},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.42195606231689453},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2799991965293884}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9338865280151367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242771983146667},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7074883580207825},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6934597492218018},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6208793520927429},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6029799580574036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45457005500793457},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45008060336112976},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43294376134872437},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.42195606231689453},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2799991965293884},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1536373746","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W2024490156","https://openalex.org/W2031647436","https://openalex.org/W2041498927","https://openalex.org/W2048142341","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2078528584","https://openalex.org/W2141998673","https://openalex.org/W2144786298","https://openalex.org/W2156379660","https://openalex.org/W2291877678","https://openalex.org/W2405774341","https://openalex.org/W2561557072","https://openalex.org/W2678916739","https://openalex.org/W2774389566","https://openalex.org/W2785523195","https://openalex.org/W2803417661","https://openalex.org/W2889442120","https://openalex.org/W2962866211","https://openalex.org/W2963285578","https://openalex.org/W6632096820","https://openalex.org/W6638667902","https://openalex.org/W6685562342","https://openalex.org/W6713658392","https://openalex.org/W6746567100","https://openalex.org/W6747620207"],"related_works":["https://openalex.org/W3016163030","https://openalex.org/W2980451698","https://openalex.org/W2921683566","https://openalex.org/W4205664022","https://openalex.org/W2102004389","https://openalex.org/W2620812332","https://openalex.org/W4210266374","https://openalex.org/W2006129368","https://openalex.org/W2907228390","https://openalex.org/W3000647100"],"abstract_inverted_index":{"Phase":[0],"is":[1],"important":[2],"for":[3,70,80,105,115],"perceptual":[4,92],"quality":[5],"in":[6,27],"speech":[7,43,84],"enhancement.":[8,85],"However,":[9],"it":[10],"seems":[11],"intractable":[12],"to":[13,22,34,76,126],"directly":[14],"estimate":[15,35],"phase":[16,28,54],"spectrogram":[17],"through":[18],"supervised":[19],"learning":[20],"due":[21],"lack":[23],"of":[24,41,46,56,88,131],"clear":[25],"structure":[26],"spectrogram.":[29],"Complex":[30],"spectral":[31,72,107,117],"mapping":[32],"aims":[33],"the":[36,94,129,135],"real":[37],"and":[38,53,82,91,134],"imaginary":[39],"spectrograms":[40],"clean":[42],"from":[44],"those":[45],"noisy":[47,57],"speech,":[48],"which":[49,74],"simultaneously":[50],"enhances":[51],"magnitude":[52,116],"responses":[55],"speech.":[58],"In":[59,86],"this":[60],"paper,":[61],"we":[62],"propose":[63],"a":[64,77,112,122],"new":[65],"convolutional":[66,101],"recurrent":[67],"network":[68,103],"(CRN)":[69],"complex":[71,106],"mapping,":[73,108],"leads":[75],"causal":[78],"system":[79],"noise-":[81],"speaker-independent":[83],"terms":[87],"objective":[89],"intelligibility":[90],"quality,":[93],"proposed":[95],"CRN":[96,114],"significantly":[97],"outperforms":[98],"an":[99],"existing":[100],"neural":[102],"(CNN)":[104],"as":[109,111],"well":[110],"strong":[113],"mapping.":[118],"We":[119],"additionally":[120],"incorporate":[121],"newly-developed":[123],"group":[124],"strategy":[125],"substantially":[127],"reduce":[128],"number":[130],"trainable":[132],"parameters":[133],"computational":[136],"cost":[137],"without":[138],"sacrificing":[139],"performance.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}