{"id":"https://openalex.org/W4391021554","doi":"https://doi.org/10.1109/asru57964.2023.10389770","title":"An Exploration of Task-Decoupling on Two-Stage Neural Post Filter for Real-Time Personalized Acoustic Echo Cancellation","display_name":"An Exploration of Task-Decoupling on Two-Stage Neural Post Filter for Real-Time Personalized Acoustic Echo Cancellation","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021554","doi":"https://doi.org/10.1109/asru57964.2023.10389770"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389770","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100410545","display_name":"Zihan Zhang","orcid":"https://orcid.org/0000-0002-0415-7721"},"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":"Zihan Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","ByteDance, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032074032","display_name":"Jiayao Sun","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":"Jiayao Sun","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026706296","display_name":"Xianjun Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianjun Xia","raw_affiliation_strings":["ByteDance,China","ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,China","institution_ids":[]},{"raw_affiliation_string":"ByteDance, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332232","display_name":"Ziqian Wang","orcid":"https://orcid.org/0009-0006-9496-2244"},"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":"Ziqian Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001664777","display_name":"Xiaopeng Yan","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":"Xiaopeng Yan","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032657764","display_name":"Yijian Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijian Xiao","raw_affiliation_strings":["ByteDance,China","ByteDance, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,China","institution_ids":[]},{"raw_affiliation_string":"ByteDance, China","institution_ids":[]}]},{"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&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP&#x0040;NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100410545"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20316705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.7489438056945801},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.7302263975143433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6301122903823853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5061563849449158},{"id":"https://openalex.org/keywords/adaptive-filter","display_name":"Adaptive filter","score":0.4507392644882202},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4313364624977112},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41792139410972595},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.38949054479599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3507629334926605},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.23745349049568176},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1581765115261078},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15049970149993896},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11142310500144958},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.09806472063064575}],"concepts":[{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.7489438056945801},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.7302263975143433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6301122903823853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5061563849449158},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.4507392644882202},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4313364624977112},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41792139410972595},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.38949054479599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3507629334926605},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.23745349049568176},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1581765115261078},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15049970149993896},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11142310500144958},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.09806472063064575},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389770","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2593116425","https://openalex.org/W2770119437","https://openalex.org/W2962935966","https://openalex.org/W2973062255","https://openalex.org/W3024869864","https://openalex.org/W3120336970","https://openalex.org/W3160115460","https://openalex.org/W3161140524","https://openalex.org/W3196995871","https://openalex.org/W3197034572","https://openalex.org/W3203083806","https://openalex.org/W3206706278","https://openalex.org/W4221155601","https://openalex.org/W4224919230","https://openalex.org/W4224919629","https://openalex.org/W4224932531","https://openalex.org/W4225905067","https://openalex.org/W4281484853","https://openalex.org/W4281712850","https://openalex.org/W4287764678","https://openalex.org/W4313178358","https://openalex.org/W4372260233","https://openalex.org/W4372265824","https://openalex.org/W4372340947","https://openalex.org/W4372346434","https://openalex.org/W4372346771","https://openalex.org/W4385822691","https://openalex.org/W6746278845","https://openalex.org/W6779079847","https://openalex.org/W6838838051","https://openalex.org/W6851662581"],"related_works":["https://openalex.org/W1473737476","https://openalex.org/W2954392969","https://openalex.org/W2162631815","https://openalex.org/W3124166275","https://openalex.org/W2026859618","https://openalex.org/W812148123","https://openalex.org/W2103984789","https://openalex.org/W2004466918","https://openalex.org/W2112363686","https://openalex.org/W1550896938"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"based":[2],"techniques":[3],"have":[4],"been":[5],"popularly":[6],"adopted":[7,39],"in":[8,28,40,58,72],"acoustic":[9,30],"echo":[10,31,97],"cancellation":[11,32,98],"(AEC).":[12],"Utilization":[13],"of":[14,21],"speaker":[15,64,70],"representation":[16,65],"has":[17],"extended":[18],"the":[19,46,78,96,107,114],"frontier":[20],"AEC,":[22],"thus":[23],"attracting":[24],"many":[25],"researchers\u2019":[26],"interest":[27],"personalized":[29],"(PAEC).":[33],"Meanwhile,":[34],"task-decoupling":[35,47,55,79,108],"strategies":[36,112],"are":[37,117],"widely":[38],"speech":[41,103],"enhancement.":[42],"To":[43],"further":[44],"explore":[45],"approach,":[48],"we":[49],"propose":[50],"to":[51,68,94],"use":[52],"a":[53,61,86],"two-stage":[54,115],"post-filter":[56],"(TDPF)":[57],"PAEC.":[59,73],"Furthermore,":[60],"multi-scale":[62],"local-global":[63],"is":[66,93],"applied":[67],"improve":[69],"extraction":[71],"Experimental":[74],"results":[75],"indicate":[76],"that":[77],"model":[80,116],"can":[81],"yield":[82],"better":[83],"performance":[84],"than":[85],"single":[87],"joint":[88],"network.":[89],"The":[90],"optimal":[91,110],"approach":[92],"decouple":[95],"from":[99],"noise":[100],"and":[101],"interference":[102],"suppression.":[104],"Based":[105],"on":[106],"sequence,":[109],"training":[111],"for":[113],"explored":[118],"afterwards.":[119]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
