{"id":"https://openalex.org/W4224917453","doi":"https://doi.org/10.1109/icassp43922.2022.9747578","title":"FRCRN: Boosting Feature Representation Using Frequency Recurrence for Monaural Speech Enhancement","display_name":"FRCRN: Boosting Feature Representation Using Frequency Recurrence for Monaural Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917453","doi":"https://doi.org/10.1109/icassp43922.2022.9747578"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747578","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/A5103758307","display_name":"Shengkui Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shengkui Zhao","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749734","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9030-7393"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076817923","display_name":"Karn N. Watcharasupat","orcid":"https://orcid.org/0000-0002-3878-5048"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Karn N. Watcharasupat","raw_affiliation_strings":["Nanyang Technological University (NTU),School of Electrical and Electronic Engineering,Singapore","School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University (NTU),School of Electrical and Electronic Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072584895","display_name":"Woon\u2010Seng Gan","orcid":"https://orcid.org/0000-0002-7143-1823"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Woon-Seng Gan","raw_affiliation_strings":["Nanyang Technological University (NTU),School of Electrical and Electronic Engineering,Singapore","School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University (NTU),School of Electrical and Electronic Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103758307"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":10.3261,"has_fulltext":false,"cited_by_count":92,"citation_normalized_percentile":{"value":0.98898332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9281","last_page":"9285"},"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.7270176410675049},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5832540988922119},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.577444851398468},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5712873935699463},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5383551716804504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5354034900665283},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5179663896560669},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.5052252411842346},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47279995679855347},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.45301324129104614},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.44651922583580017},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42846179008483887},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.19889631867408752},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1419127881526947},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1068306565284729},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08918356895446777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7270176410675049},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5832540988922119},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.577444851398468},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5712873935699463},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5383551716804504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354034900665283},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5179663896560669},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.5052252411842346},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47279995679855347},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.45301324129104614},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.44651922583580017},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42846179008483887},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.19889631867408752},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1419127881526947},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1068306565284729},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08918356895446777},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/icassp43922.2022.9747578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747578","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2144404214","https://openalex.org/W2291877678","https://openalex.org/W2516547830","https://openalex.org/W2603567530","https://openalex.org/W2889442120","https://openalex.org/W2891433113","https://openalex.org/W2962843322","https://openalex.org/W2963308316","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W2998161426","https://openalex.org/W3095057960","https://openalex.org/W3096159803","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3160085755","https://openalex.org/W3161480375","https://openalex.org/W3162188526","https://openalex.org/W3162493033","https://openalex.org/W3162501355","https://openalex.org/W3163827866","https://openalex.org/W3195288392","https://openalex.org/W3197912330","https://openalex.org/W3198680319","https://openalex.org/W3213188934","https://openalex.org/W4225905067","https://openalex.org/W6738884980","https://openalex.org/W6785195226","https://openalex.org/W6785764544","https://openalex.org/W6796856108"],"related_works":["https://openalex.org/W3112081258","https://openalex.org/W2332949289","https://openalex.org/W98805669","https://openalex.org/W2315892906","https://openalex.org/W2792514479","https://openalex.org/W2392214114","https://openalex.org/W4384026382","https://openalex.org/W4390516098","https://openalex.org/W1973326588","https://openalex.org/W2808425152"],"abstract_inverted_index":{"Convolutional":[0],"recurrent":[1,12,48],"networks":[2],"(CRN)":[3],"integrating":[4],"a":[5,11,46,101],"convolutional":[6,47,67],"encoder-decoder":[7,49],"(CED)":[8],"structure":[9,13,51],"and":[10,86,119,150,156,169,185],"have":[14],"achieved":[15,162,170],"promising":[16],"performance":[17,164],"for":[18,173],"monaural":[19],"speech":[20,91],"enhancement.":[21],"However,":[22],"feature":[23,54,68,88],"representation":[24,55],"across":[25],"frequency":[26,58,63,72,84,95],"context":[27],"is":[28,79,97],"highly":[29],"constrained":[30],"due":[31],"to":[32,52,122,140],"limited":[33],"receptive":[34],"fields":[35],"in":[36,147,178,189],"the":[37,57,71,108,117,120,129,174,190],"convolutions":[38],"of":[39,81,90,180],"CED.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,110],"propose":[45],"(CRED)":[50],"boost":[53],"along":[56,70],"axis.":[59],"The":[60,93],"CRED":[61],"applies":[62],"recurrence":[64,96],"on":[65,165],"3D":[66],"maps":[69],"axis":[73],"following":[74],"each":[75],"convolution,":[76],"therefore,":[77],"it":[78],"capable":[80],"catching":[82],"long-range":[83],"correlations":[85],"enhancing":[87],"representations":[89],"inputs.":[92],"proposed":[94,130,160],"realized":[98],"efficiently":[99],"using":[100,153],"feedforward":[102],"sequential":[103],"memory":[104],"network":[105],"(FSMN).":[106],"Besides":[107],"CRED,":[109],"insert":[111],"two":[112],"stacked":[113],"FSMN":[114],"layers":[115],"between":[116],"encoder":[118],"decoder":[121],"model":[123],"further":[124],"temporal":[125],"dynamics.":[126],"We":[127,137],"name":[128],"framework":[131],"as":[132],"Frequency":[133],"Recurrent":[134],"CRN":[135],"(FRCRN).":[136],"design":[138],"FRCRN":[139,152],"predict":[141],"complex":[142],"Ideal":[143],"Ratio":[144],"Mask":[145],"(cIRM)":[146],"complex-valued":[148],"domain":[149],"optimize":[151],"both":[154],"time-frequency-domain":[155],"time-domain":[157],"losses.":[158],"Our":[159],"approach":[161],"state-of-the-art":[163],"wideband":[166],"bench-mark":[167],"datasets":[168],"2nd":[171],"place":[172],"real-time":[175],"fullband":[176],"track":[177],"terms":[179],"Mean":[181],"Opinion":[182],"Score":[183],"(MOS)":[184],"Word":[186],"Accuracy":[187],"(WAcc)":[188],"ICASSP":[191],"2022":[192],"Deep":[193],"Noise":[194],"Suppression":[195],"(DNS)":[196],"challenge.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}