{"id":"https://openalex.org/W4224934178","doi":"https://doi.org/10.1109/icassp43922.2022.9746020","title":"Uformer: A Unet Based Dilated Complex & Real Dual-Path Conformer Network for Simultaneous Speech Enhancement and Dereverberation","display_name":"Uformer: A Unet Based Dilated Complex & Real Dual-Path Conformer Network for Simultaneous Speech Enhancement and Dereverberation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224934178","doi":"https://doi.org/10.1109/icassp43922.2022.9746020"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746020","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/A5010250251","display_name":"Yihui Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yihui Fu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657452","display_name":"Yun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134178","display_name":"Sohu (China)","ror":"https://ror.org/02sfdh709","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210134178"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liu","raw_affiliation_strings":["Sogou Inc.,AI Interaction Division,Beijing,China","AI Interaction Division, Sogou Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sogou Inc.,AI Interaction Division,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"AI Interaction Division, Sogou Inc., Beijing, China","institution_ids":["https://openalex.org/I4210134178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642253","display_name":"Jingdong Li","orcid":"https://orcid.org/0000-0003-2335-6280"},"institutions":[{"id":"https://openalex.org/I4210134178","display_name":"Sohu (China)","ror":"https://ror.org/02sfdh709","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210134178"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Li","raw_affiliation_strings":["Sogou Inc.,AI Interaction Division,Beijing,China","AI Interaction Division, Sogou Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sogou Inc.,AI Interaction Division,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"AI Interaction Division, Sogou Inc., Beijing, China","institution_ids":["https://openalex.org/I4210134178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101954584","display_name":"Dawei Luo","orcid":"https://orcid.org/0009-0000-1875-0262"},"institutions":[{"id":"https://openalex.org/I4210134178","display_name":"Sohu (China)","ror":"https://ror.org/02sfdh709","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210134178"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Luo","raw_affiliation_strings":["Sogou Inc.,AI Interaction Division,Beijing,China","AI Interaction Division, Sogou Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sogou Inc.,AI Interaction Division,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"AI Interaction Division, Sogou Inc., Beijing, China","institution_ids":["https://openalex.org/I4210134178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017208328","display_name":"Shubo Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shubo Lv","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031232410","display_name":"Yukai Jv","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukai Jv","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5010250251"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":5.8989,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.97503949,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7417","last_page":"7421"},"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":0.998199999332428,"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/T13289","display_name":"Infant Health and Development","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8104478120803833},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6921941041946411},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5138350129127502},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49670273065567017},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47468921542167664},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.46747279167175293},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4402041435241699},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4276971220970154},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36687058210372925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3495813012123108},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.18818262219429016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8104478120803833},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6921941041946411},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5138350129127502},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49670273065567017},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47468921542167664},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.46747279167175293},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4402041435241699},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4276971220970154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36687058210372925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3495813012123108},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.18818262219429016},{"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/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":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746020","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","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2048142341","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2117678320","https://openalex.org/W2219249508","https://openalex.org/W2609317876","https://openalex.org/W2800675406","https://openalex.org/W2952218014","https://openalex.org/W2963992487","https://openalex.org/W2964058413","https://openalex.org/W2972359262","https://openalex.org/W2973133192","https://openalex.org/W2991361823","https://openalex.org/W2998161426","https://openalex.org/W3015199127","https://openalex.org/W3015651375","https://openalex.org/W3094002217","https://openalex.org/W3096408984","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3120336970","https://openalex.org/W3138190329","https://openalex.org/W3158779859","https://openalex.org/W3161480375","https://openalex.org/W3161950572","https://openalex.org/W3163842642","https://openalex.org/W3197042120","https://openalex.org/W3197260772","https://openalex.org/W3198661668","https://openalex.org/W3198680319","https://openalex.org/W3213188934","https://openalex.org/W4324296897","https://openalex.org/W4385245566","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6785090365","https://openalex.org/W6791885954","https://openalex.org/W6794544138","https://openalex.org/W6796687826","https://openalex.org/W6796856108"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2119949815"],"abstract_inverted_index":{"Complex":[0],"spectrum":[1,113],"and":[2,13,46,53,60,67,71,98,104,114,116,136,145,150],"magnitude":[3,47,115],"are":[4,106,185],"considered":[5],"as":[6],"two":[7,20,122],"major":[8],"features":[9,21],"of":[10,162],"speech":[11,51,96],"enhancement":[12,52,97],"dereverberation.":[14,54],"Traditional":[15],"approaches":[16],"always":[17],"treat":[18],"these":[19],"separately,":[22],"ignoring":[23],"their":[24],"underlying":[25],"relationship.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"propose":[31],"Uformer,":[32],"a":[33],"Unet":[34],"based":[35],"dilated":[36,61,86],"complex":[37,45,87,112,146],"&":[38,88],"real":[39,89],"dual-path":[40,90],"conformer":[41,91],"network":[42],"in":[43,83],"both":[44],"domain":[48,147],"for":[49],"simultaneous":[50],"We":[55,172],"exploit":[56],"time":[57,144],"attention":[58,73,126],"(TA)":[59],"convolution":[62],"(DC)":[63],"to":[64,75,108,130,178],"leverage":[65],"local":[66],"global":[68],"contextual":[69],"information":[70,119],"frequency":[72],"(FA)":[74],"model":[76,110],"dimensional":[77],"information.":[78],"These":[79],"three":[80],"sub-modules":[81],"contained":[82],"the":[84,95,111,118,132,158],"proposed":[85,182],"module":[92],"effectively":[93],"improve":[94],"dereverberation":[99],"performance.":[100],"Furthermore,":[101],"hybrid":[102],"encoder":[103,135],"decoder":[105,125],"adopted":[107],"simultaneously":[109],"promote":[117],"interaction":[120,133],"between":[121,134],"domains.":[123],"Encoder":[124],"is":[127],"also":[128,173],"applied":[129],"enhance":[131],"decoder.":[137],"Our":[138],"experimental":[139],"results":[140],"outperform":[141],"all":[142,169,181],"SOTA":[143],"models":[148],"objectively":[149],"subjectively.":[151],"Specifically,":[152],"Uformer":[153],"reaches":[154],"3.6032":[155],"DNSMOS":[156],"on":[157],"blind":[159],"test":[160],"set":[161],"Interspeech":[163],"2021":[164],"DNS":[165],"Challenge,":[166],"which":[167],"outperforms":[168],"top-performed":[170],"models.":[171],"carry":[174],"out":[175],"ablation":[176],"experiments":[177],"tease":[179],"apart":[180],"submodules":[183],"that":[184],"most":[186],"important.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}