{"id":"https://openalex.org/W4372260471","doi":"https://doi.org/10.1109/icassp49357.2023.10095716","title":"A Lightweight Fourier Convolutional Attention Encoder for Multi-Channel Speech Enhancement","display_name":"A Lightweight Fourier Convolutional Attention Encoder for Multi-Channel Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260471","doi":"https://doi.org/10.1109/icassp49357.2023.10095716"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5102014331","display_name":"Siyu Sun","orcid":"https://orcid.org/0009-0003-0861-8788"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Siyu Sun","raw_affiliation_strings":["ByteDance,RTC Lab,China","RTC Lab, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,RTC Lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"RTC Lab, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678706","display_name":"Jian Jin","orcid":"https://orcid.org/0000-0003-4250-1519"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Jin","raw_affiliation_strings":["ByteDance,RTC Lab,China","RTC Lab, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,RTC Lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"RTC Lab, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078536360","display_name":"Zhe Han","orcid":"https://orcid.org/0000-0002-5177-7798"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Han","raw_affiliation_strings":["ByteDance,RTC Lab,China","RTC Lab, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,RTC Lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"RTC Lab, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049790194","display_name":"Xianjun Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianjun Xia","raw_affiliation_strings":["ByteDance,RTC Lab,China","RTC Lab, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,RTC Lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"RTC Lab, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379287","display_name":"Li Chen","orcid":"https://orcid.org/0000-0002-8664-1276"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":["ByteDance,RTC Lab,China","RTC Lab, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,RTC Lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"RTC Lab, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046445492","display_name":"Yijian Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijian Xiao","raw_affiliation_strings":["ByteDance,RTC Lab,China","RTC Lab, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,RTC Lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"RTC Lab, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057778593","display_name":"Piao Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Piao Ding","raw_affiliation_strings":["ByteDance,RTC Lab,China","RTC Lab, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,RTC Lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"RTC Lab, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073073496","display_name":"Shenyi Song","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenyi Song","raw_affiliation_strings":["ByteDance,RTC Lab,China","RTC Lab, ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,RTC Lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"RTC Lab, ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017213156","display_name":"Roberto Togneri","orcid":"https://orcid.org/0000-0002-3778-4633"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Roberto Togneri","raw_affiliation_strings":["University of Western Australia,School of Engineering, Electrical, Electronic and Computer Engineering,Perth,Australia","School of Engineering, Electrical, Electronic and Computer Engineering, University of Western Australia, Perth, Australia"],"affiliations":[{"raw_affiliation_string":"University of Western Australia,School of Engineering, Electrical, Electronic and Computer Engineering,Perth,Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"School of Engineering, Electrical, Electronic and Computer Engineering, University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003692319","display_name":"Haijian Zhang","orcid":"https://orcid.org/0000-0001-8314-6563"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijian Zhang","raw_affiliation_strings":["WuHan University,School of Electronic Information,WuHan,China","School of Electronic Information, WuHan University, WuHan, China"],"affiliations":[{"raw_affiliation_string":"WuHan University,School of Electronic Information,WuHan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Electronic Information, WuHan University, WuHan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5102014331"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":1.1824,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7817642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7993177175521851},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7132449746131897},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.702284038066864},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6761491298675537},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6048259139060974},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6031089425086975},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6015224456787109},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5544191002845764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4952222406864166},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4738735854625702},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41540271043777466},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39155521988868713},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.37632808089256287},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13576728105545044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993177175521851},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7132449746131897},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.702284038066864},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6761491298675537},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6048259139060974},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6031089425086975},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6015224456787109},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5544191002845764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4952222406864166},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4738735854625702},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41540271043777466},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39155521988868713},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.37632808089256287},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13576728105545044},{"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/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/9a29fa26-1dd6-4199-8bb2-f8ed940ef2ac","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/9a29fa26-1dd6-4199-8bb2-f8ed940ef2ac","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sun , S , Jin , J , Han , Z , Xia , X , Chen , L , Xiao , Y , Ding , P , Song , S , Togneri , R & Zhang , H 2023 , A Lightweight Fourier Convolutional Attention Encoder for Multi-Channel Speech Enhancement . in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing . ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings , vol. 2023-June , IEEE, Institute of Electrical and Electronics Engineers , 48th IEEE International Conference on Acoustics, Speech and Signal Processing , Rhodes Island , Greece , 4/06/23 . https://doi.org/10.1109/ICASSP49357.2023.10095716","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2067295501","https://openalex.org/W2117678320","https://openalex.org/W2144404214","https://openalex.org/W2219249508","https://openalex.org/W2398042854","https://openalex.org/W2516001803","https://openalex.org/W2517616541","https://openalex.org/W2568308529","https://openalex.org/W2593116425","https://openalex.org/W2884585870","https://openalex.org/W2937525188","https://openalex.org/W2962843322","https://openalex.org/W2963242190","https://openalex.org/W2963302875","https://openalex.org/W3004309045","https://openalex.org/W3094002217","https://openalex.org/W3096408984","https://openalex.org/W3103556460","https://openalex.org/W3162188526","https://openalex.org/W3162341667","https://openalex.org/W3196940724","https://openalex.org/W3198027828","https://openalex.org/W3198511309","https://openalex.org/W3199003182","https://openalex.org/W4221149546","https://openalex.org/W4221165117","https://openalex.org/W4224917453","https://openalex.org/W4226071457","https://openalex.org/W4296068754","https://openalex.org/W6688816777","https://openalex.org/W6744786301","https://openalex.org/W6748730751","https://openalex.org/W6753412334","https://openalex.org/W6785090365","https://openalex.org/W6785302134","https://openalex.org/W6801401839","https://openalex.org/W6810528592","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"Beamforming":[0],"weights":[1,26,38],"prediction":[2],"via":[3],"deep":[4,102],"neural":[5],"networks":[6],"has":[7],"been":[8],"one":[9],"of":[10,42,73,130,138],"the":[11,36,66,71,122,136,139,155],"main":[12],"methods":[13],"in":[14,24,89],"multi-channel":[15],"speech":[16],"enhancement":[17],"tasks.":[18],"The":[19,114],"spectral-spatial":[20,44,123],"cues":[21],"are":[22,112],"crucial":[23],"beamforming":[25,37,131],"estimation,":[27],"however,":[28],"many":[29],"existing":[30],"works":[31],"fail":[32],"to":[33,59,120,126,152],"optimally":[34],"predict":[35],"with":[39,97,142],"an":[40],"absence":[41],"adequate":[43],"information":[45,125],"learning.":[46],"To":[47],"tackle":[48],"this":[49,90],"challenge,":[50],"we":[51],"propose":[52],"a":[53,61,80,101,147],"Fourier":[54],"convolutional":[55,82],"attention":[56,95],"encoder":[57],"(FCAE)":[58],"provide":[60],"global":[62],"receptive":[63],"field":[64],"over":[65],"frequency":[67],"axis":[68],"and":[69,76,100,146],"boost":[70],"learning":[72],"spectral":[74],"contexts":[75],"cross-channel":[77],"features.":[78],"Besides,":[79],"new":[81],"recurrent":[83,110],"encoder-decoder":[84],"(CRED)":[85],"structure":[86,117],"is":[87,118],"proposed":[88,115,140],"work,":[91],"within":[92],"which":[93],"FCAEs,":[94],"blocks":[96],"skip":[98],"connections":[99],"feedback":[103],"sequential":[104],"memory":[105],"network":[106],"(DFSMN)":[107],"serving":[108],"as":[109],"module":[111],"involved.":[113],"CRED":[116],"exploited":[119],"capture":[121],"joint":[124],"obtain":[127],"accurate":[128],"estimation":[129],"weights.":[132],"Experimental":[133],"results":[134],"demonstrate":[135],"superiority":[137],"approach":[141],"only":[143],"0.74M":[144],"parameters":[145],"PESQ":[148],"improvement":[149],"from":[150],"2.225":[151],"2.359":[153],"on":[154],"ConferencingSpeech2021":[156],"challenge":[157],"development":[158],"test":[159],"set.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}