{"id":"https://openalex.org/W4221155601","doi":"https://doi.org/10.1109/icassp43922.2022.9746733","title":"Multi-Task Deep Residual Echo Suppression with Echo-Aware Loss","display_name":"Multi-Task Deep Residual Echo Suppression with Echo-Aware Loss","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221155601","doi":"https://doi.org/10.1109/icassp43922.2022.9746733"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746733","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2202.06850","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068686249","display_name":"Shimin Zhang","orcid":"https://orcid.org/0000-0001-6213-4483"},"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":"Shimin Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101673728","display_name":"Ziteng Wang","orcid":"https://orcid.org/0009-0001-8487-8093"},"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":"Ziteng Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"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@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yihui Fu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069657933","display_name":"Biao Tian","orcid":"https://orcid.org/0000-0001-7259-3739"},"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":"Biao Tian","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101844257","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0001-7780-7185"},"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":"Qiang Fu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365442","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0002-2994-6743"},"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), School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9127","last_page":"9131"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9977999925613403,"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/echo","display_name":"Echo (communications protocol)","score":0.8653427958488464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6701503396034241},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.564095675945282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.563245415687561},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5283594727516174},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4859798848628998},{"id":"https://openalex.org/keywords/adaptive-filter","display_name":"Adaptive filter","score":0.4653758406639099},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4464954137802124},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42257586121559143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3911622166633606},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29236817359924316},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.18165668845176697},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1740812361240387},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13043278455734253},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.08474874496459961}],"concepts":[{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.8653427958488464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6701503396034241},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.564095675945282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.563245415687561},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5283594727516174},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4859798848628998},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.4653758406639099},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4464954137802124},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42257586121559143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3911622166633606},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29236817359924316},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.18165668845176697},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1740812361240387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13043278455734253},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.08474874496459961},{"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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746733","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"},{"id":"pmh:oai:arXiv.org:2202.06850","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.06850","pdf_url":"https://arxiv.org/pdf/2202.06850","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2202.06850","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.06850","pdf_url":"https://arxiv.org/pdf/2202.06850","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W88988980","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1973524311","https://openalex.org/W2046317813","https://openalex.org/W2102800590","https://openalex.org/W2168837669","https://openalex.org/W2291522532","https://openalex.org/W2547875792","https://openalex.org/W2888860279","https://openalex.org/W2963308316","https://openalex.org/W2972745527","https://openalex.org/W3095057960","https://openalex.org/W3096408984","https://openalex.org/W3160115460","https://openalex.org/W3160394811","https://openalex.org/W3162616235","https://openalex.org/W3163136406","https://openalex.org/W3194338569","https://openalex.org/W3195156220","https://openalex.org/W3196995871","https://openalex.org/W3197034572","https://openalex.org/W3197042120","https://openalex.org/W3201648151","https://openalex.org/W3206246883","https://openalex.org/W3213305849","https://openalex.org/W4224919230","https://openalex.org/W4225873749","https://openalex.org/W4286902322","https://openalex.org/W4287764678","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6729448088","https://openalex.org/W6767367760","https://openalex.org/W6779079847","https://openalex.org/W6802844217","https://openalex.org/W6810582601"],"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":{"This":[0],"paper":[1],"introduces":[2],"the":[3,8,34,39,42,56,60,86,105,122,131,138,165,172,176,188,193,201,210,221],"NWPU":[4],"Team\u2019s":[5],"entry":[6],"to":[7,31,88,121,127,148],"ICASSP":[9,194],"2022":[10,195],"AEC":[11,22],"Challenge.":[12],"We":[13,47],"take":[14],"a":[15,20,24,63,69,183],"hybrid":[16],"approach":[17,198],"that":[18,92,137,170],"cascades":[19],"linear":[21,35,173],"with":[23,33,82,85,156],"neural":[25,52,145,180],"post-filter.":[26,166],"The":[27],"former":[28],"is":[29,75,182],"used":[30],"deal":[32],"echo":[36,45,83,174],"components":[37],"while":[38],"latter":[40],"suppresses":[41],"residual":[43],"non-linear":[44],"components.":[46],"use":[48],"gated":[49],"convolutional":[50],"F-T-LSTM":[51],"network":[53],"(GFTNN)":[54],"as":[55,77,175],"backbone":[57],"and":[58,152,209,220],"shape":[59],"post-filter":[61,146,181],"by":[62],"multi-task":[64],"learning":[65],"(MTL)":[66],"framework,":[67],"where":[68,104],"voice":[70],"activity":[71],"detection":[72],"(VAD)":[73],"module":[74,143],"adopted":[76],"an":[78,100,153],"auxiliary":[79],"task":[80],"along":[81],"suppression,":[84],"aim":[87],"avoid":[89],"over":[90],"suppression":[91,129],"may":[93],"cause":[94],"speech":[95],"distortion.":[96],"Moreover,":[97],"we":[98,168],"adopt":[99],"echo-aware":[101],"loss":[102,110],"function,":[103],"mean":[106,215],"square":[107],"error":[108],"(MSE)":[109],"can":[111],"be":[112],"optimized":[113],"particularly":[114],"for":[115,164],"every":[116],"time-frequency":[117],"bin":[118],"(TF-bin)":[119],"according":[120],"signal-to-echo":[123],"ratio":[124],"(SER),":[125],"leading":[126],"further":[128],"on":[130,204,213],"echo.":[132],"Extensive":[133],"ablation":[134],"study":[135],"shows":[136],"time":[139],"delay":[140],"estimation":[141],"(TDE)":[142],"in":[144],"leads":[147],"better":[149,157,184],"perceptual":[150],"quality,":[151],"adaptive":[154],"filter":[155],"convergence":[158],"will":[159],"bring":[160],"consistent":[161],"performance":[162],"gain":[163],"Besides,":[167],"find":[169],"using":[171,187],"input":[177],"of":[178],"our":[179,197],"choice":[185],"than":[186],"reference":[189],"signal":[190],"directly.":[191],"In":[192],"AEC-Challenge,":[196],"has":[199],"ranked":[200],"1st":[202],"place":[203,212],"word":[205],"accuracy":[206],"(WAcc)":[207],"(0.817)":[208],"3rd":[211],"both":[214],"opinion":[216],"score":[217,223],"(MOS)":[218],"(4.502)":[219],"final":[222],"(0.864).":[224]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
