{"id":"https://openalex.org/W4372349782","doi":"https://doi.org/10.1109/icassp49357.2023.10096930","title":"Improving Acoustic Echo Cancellation by Mixing Speech Local and Global Features with Transformer","display_name":"Improving Acoustic Echo Cancellation by Mixing Speech Local and Global Features with Transformer","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372349782","doi":"https://doi.org/10.1109/icassp49357.2023.10096930"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096930","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096930","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/A5018600252","display_name":"Yajie Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"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":"Yajie Liu","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software,School of Computer Science,China","School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software,School of Computer Science,China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050125868","display_name":"Xinmeng Xu","orcid":"https://orcid.org/0009-0008-1607-7180"},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"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":"Xinmeng Xu","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software,School of Computer Science,China","School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software,School of Computer Science,China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041664453","display_name":"Weiping Tu","orcid":"https://orcid.org/0000-0002-6933-3298"},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"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":"Weiping Tu","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software,School of Computer Science,China","Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, China","School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software,School of Computer Science,China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102859655","display_name":"Yuhong Yang","orcid":"https://orcid.org/0000-0003-3001-7957"},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"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":"Yuhong Yang","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software,School of Computer Science,China","School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, China","Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software,School of Computer Science,China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102764683","display_name":"Xiao Li","orcid":"https://orcid.org/0000-0003-0186-1788"},"institutions":[{"id":"https://openalex.org/I174442536","display_name":"South Central Minzu University","ror":"https://ror.org/03d7sax13","country_code":"CN","type":"education","lineage":["https://openalex.org/I174442536"]},{"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":"Li Xiao","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software,School of Computer Science,China","School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software,School of Computer Science,China","institution_ids":["https://openalex.org/I174442536"]},{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3695,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52779497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"14","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":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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":0.7087923884391785},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6391227841377258},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5835967063903809},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5278090238571167},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5107100009918213},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4542922377586365},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41735589504241943},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41387641429901123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3482058644294739},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16557559370994568},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12120375037193298},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09481114149093628},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06853368878364563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7087923884391785},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6391227841377258},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5835967063903809},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5278090238571167},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5107100009918213},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4542922377586365},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41735589504241943},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41387641429901123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3482058644294739},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16557559370994568},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12120375037193298},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09481114149093628},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06853368878364563},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096930","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096930","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W123803282","https://openalex.org/W2065804682","https://openalex.org/W2067295501","https://openalex.org/W2127851351","https://openalex.org/W2531409750","https://openalex.org/W2804036797","https://openalex.org/W3015199127","https://openalex.org/W3095853290","https://openalex.org/W3096893582","https://openalex.org/W3130911052","https://openalex.org/W3160115460","https://openalex.org/W3163838195","https://openalex.org/W3197034572","https://openalex.org/W3197042120","https://openalex.org/W3198008448","https://openalex.org/W3198845391","https://openalex.org/W4224919230","https://openalex.org/W4224933821","https://openalex.org/W4297841744","https://openalex.org/W4385245566","https://openalex.org/W6728184133","https://openalex.org/W6739901393","https://openalex.org/W6790994528"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2357191878","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W1997078944","https://openalex.org/W1968065688","https://openalex.org/W4220830676","https://openalex.org/W2142945567","https://openalex.org/W1552846815","https://openalex.org/W4221144054"],"abstract_inverted_index":{"We":[0],"propose":[1,88],"MiT-Net,":[2],"a":[3,9,31,43,62,83,89,91,99],"novel":[4],"mix-transformer":[5,142],"neural":[6],"network":[7],"with":[8],"pyramid":[10,63],"encoder":[11],"operating":[12],"in":[13,36,82,98,122],"the":[14,18,50,67,72,115,131,141,145,153],"time":[15],"domain,":[16],"for":[17,109],"task":[19],"of":[20,55,93,124],"acoustic":[21,27],"echo":[22,28],"cancellation.":[23],"The":[24],"MiT-Net":[25],"formulates":[26],"cancellation":[29],"as":[30],"supervised":[32],"speech":[33,39,107,134],"separation":[34],"problem,":[35],"which":[37,65],"near-end":[38],"is":[40],"separated":[41],"from":[42],"single":[44],"microphone":[45],"recording":[46],"and":[47,53,78,95,105,136,148],"sent":[48],"to":[49,70,79,102],"far":[51],"end,":[52],"consists":[54],"two":[56],"key":[57],"components.":[58],"First,":[59],"we":[60,87],"apply":[61],"encoder,":[64],"adopts":[66],"coarse-to-fine":[68],"structure,":[69],"extract":[71],"latent":[73],"correlations":[74],"between":[75,133],"double-end":[76],"signals":[77],"fuse":[80],"them":[81],"multiscale":[84],"manner.":[85],"Second,":[86],"mix-transformer,":[90],"combination":[92],"local":[94,104,135],"global":[96,106,137],"attention":[97],"parallel":[100],"way,":[101],"leverage":[103],"information":[108],"separation.":[110],"Experimental":[111],"results":[112],"show":[113],"that":[114],"proposed":[116],"method":[117],"outperforms":[118],"recent":[119],"AEC":[120],"methods":[121],"terms":[123],"objective":[125],"evaluation":[126],"metrics.":[127],"In":[128],"addition,":[129],"exploring":[130],"correlation":[132],"features":[138],"by":[139],"using":[140],"significantly":[143],"improves":[144],"system":[146],"performance":[147],"shows":[149],"more":[150],"robustness":[151],"than":[152],"conventional":[154],"transformer.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
