{"id":"https://openalex.org/W3015389285","doi":"https://doi.org/10.1109/icassp40776.2020.9053508","title":"CAD-AEC: Context-Aware Deep Acoustic Echo Cancellation","display_name":"CAD-AEC: Context-Aware Deep Acoustic Echo Cancellation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015389285","doi":"https://doi.org/10.1109/icassp40776.2020.9053508","mag":"3015389285"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5029022979","display_name":"Amin Fazel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amin Fazel","raw_affiliation_strings":["Samsung SoC Multimedia R&D, San Diego, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung SoC Multimedia R&D, San Diego, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022805456","display_name":"Mostafa El\u2010Khamy","orcid":"https://orcid.org/0000-0001-9421-6037"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mostafa El-Khamy","raw_affiliation_strings":["Samsung SoC Multimedia R&D, San Diego, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung SoC Multimedia R&D, San Diego, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331815","display_name":"Jungwon Lee","orcid":"https://orcid.org/0000-0001-8922-063X"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jungwon Lee","raw_affiliation_strings":["Samsung SoC Multimedia R&D, San Diego, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung SoC Multimedia R&D, San Diego, USA","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210101778"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6919","last_page":"6923"},"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":0.9995999932289124,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.742293655872345},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7038865089416504},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5759465098381042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5462632775306702},{"id":"https://openalex.org/keywords/cad","display_name":"CAD","score":0.5436061024665833},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.538852870464325},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5101125836372375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5095372796058655},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.48044678568840027},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.45737743377685547},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4358682334423065},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4139004647731781},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3532283902168274},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17972296476364136},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11861118674278259},{"id":"https://openalex.org/keywords/engineering-drawing","display_name":"Engineering drawing","score":0.09433206915855408},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07607066631317139}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742293655872345},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7038865089416504},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5759465098381042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5462632775306702},{"id":"https://openalex.org/C194789388","wikidata":"https://www.wikidata.org/wiki/Q17855283","display_name":"CAD","level":2,"score":0.5436061024665833},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.538852870464325},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5101125836372375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5095372796058655},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.48044678568840027},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.45737743377685547},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4358682334423065},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4139004647731781},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3532283902168274},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17972296476364136},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11861118674278259},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.09433206915855408},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07607066631317139},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1924770834","https://openalex.org/W1979544118","https://openalex.org/W1999542175","https://openalex.org/W2004465649","https://openalex.org/W2038085771","https://openalex.org/W2053056809","https://openalex.org/W2065804682","https://openalex.org/W2117678320","https://openalex.org/W2133011550","https://openalex.org/W2157331557","https://openalex.org/W2162472575","https://openalex.org/W2194775991","https://openalex.org/W2395657913","https://openalex.org/W2562673262","https://openalex.org/W2785523195","https://openalex.org/W2799373327","https://openalex.org/W2888860279","https://openalex.org/W2963403868","https://openalex.org/W2972461400","https://openalex.org/W2973044449","https://openalex.org/W4385245566","https://openalex.org/W6631943919","https://openalex.org/W6640212811","https://openalex.org/W6711980375","https://openalex.org/W6739901393","https://openalex.org/W6747620207","https://openalex.org/W6751159330","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W1473737476","https://openalex.org/W2061432289","https://openalex.org/W2276571074","https://openalex.org/W637098845","https://openalex.org/W2410116073","https://openalex.org/W3044972437","https://openalex.org/W2275866607","https://openalex.org/W1908932129","https://openalex.org/W2587289131","https://openalex.org/W2365000768"],"abstract_inverted_index":{"Deep-leaming":[0],"based":[1],"acoustic":[2],"echo":[3,147],"cancellation":[4],"(AEC)":[5],"methods":[6],"have":[7,85],"been":[8],"shown":[9],"to":[10,76,157],"outperform":[11],"the":[12,19,26,58,63,73,78,89,103,114,126,140,158],"classical":[13,64,160],"techniques.":[14,164],"The":[15,54,92,109],"main":[16,52],"drawback":[17],"of":[18,57,72],"learning-based":[20],"AEC":[21,47,65,80],"is":[22,95],"its":[23,31],"dependency":[24,87],"on":[25,88,125],"training":[27,134],"set,":[28],"which":[29],"limits":[30],"practical":[32],"deployment":[33],"in":[34,129],"mobile":[35],"devices":[36],"and":[37,66,106,132,135,152,161],"unconstrained":[38],"environments.":[39],"This":[40],"paper":[41],"proposes":[42],"a":[43,96],"context-":[44],"aware":[45],"deep":[46,79,97,110,162],"(CAD-AEC)":[48],"by":[49],"introducing":[50],"two":[51],"components.":[53],"first":[55],"component":[56,94],"CAD-AEC":[59,142],"borrows":[60],"ideas":[61],"from":[62],"performs":[67],"frequency":[68],"domain":[69],"adaptive":[70],"filtering":[71],"microphone":[74],"signal,":[75],"provide":[77],"network":[81],"with":[82,119],"features":[83],"that":[84,123,139],"less":[86],"development":[90],"context.":[91,127],"second":[93],"contextual-attention":[98],"module":[99],"(CAM),":[100],"inserted":[101],"between":[102],"recurrent":[104],"encoder":[105,115],"decoder":[107],"architectures.":[108],"CAM":[111],"adaptively":[112],"scales":[113],"output":[116],"during":[117],"inference":[118],"calculated":[120],"attention":[121],"weights":[122],"depend":[124],"Experiments":[128],"both":[130],"matched":[131],"mismatched":[133],"testing":[136],"environments,":[137],"show":[138],"proposed":[141],"can":[143],"robustly":[144],"achieve":[145],"better":[146],"return":[148],"loss":[149],"enhancement":[150],"(ERLE)":[151],"perceptual":[153],"speech":[154],"quality":[155],"compared":[156],"previous":[159],"learning":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}