{"id":"https://openalex.org/W3160092772","doi":"https://doi.org/10.1109/icassp39728.2021.9414753","title":"U-Convolution Based Residual Echo Suppression with Multiple Encoders","display_name":"U-Convolution Based Residual Echo Suppression with Multiple Encoders","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160092772","doi":"https://doi.org/10.1109/icassp39728.2021.9414753","mag":"3160092772"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5073871215","display_name":"Eesung Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eesung Kim","raw_affiliation_strings":["AI R&D Team, Kakao Enterprise, Gyeonggi-do, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI R&D Team, Kakao Enterprise, Gyeonggi-do, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038521076","display_name":"Jae-Jin Jeon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jae-Jin Jeon","raw_affiliation_strings":["AI R&D Team, Kakao Enterprise, Gyeonggi-do, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI R&D Team, Kakao Enterprise, Gyeonggi-do, Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023974410","display_name":"Hyeji Seo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyeji Seo","raw_affiliation_strings":["AI R&D Team, Kakao Enterprise, Gyeonggi-do, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI R&D Team, Kakao Enterprise, Gyeonggi-do, Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1544,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41661646,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"925","last_page":"929"},"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":0.9994000196456909,"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":0.9991999864578247,"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/pesq","display_name":"PESQ","score":0.922493577003479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7630683183670044},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6914596557617188},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.688592791557312},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6710978746414185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6475217938423157},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5463989973068237},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.49609431624412537},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4906426966190338},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4609888195991516},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.429721474647522},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30181002616882324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2905682325363159},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2619606554508209},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20449388027191162},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17406105995178223},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09619084000587463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09351882338523865}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.922493577003479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630683183670044},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6914596557617188},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.688592791557312},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6710978746414185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6475217938423157},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5463989973068237},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.49609431624412537},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4906426966190338},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4609888195991516},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.429721474647522},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30181002616882324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2905682325363159},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2619606554508209},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20449388027191162},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17406105995178223},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09619084000587463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09351882338523865},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1974260473","https://openalex.org/W1974387177","https://openalex.org/W1979544118","https://openalex.org/W2049241792","https://openalex.org/W2065804682","https://openalex.org/W2067295501","https://openalex.org/W2117678320","https://openalex.org/W2166718721","https://openalex.org/W2219249508","https://openalex.org/W2292235217","https://openalex.org/W2395657913","https://openalex.org/W2531409750","https://openalex.org/W2799373327","https://openalex.org/W2888860279","https://openalex.org/W2898268964","https://openalex.org/W2952218014","https://openalex.org/W2964121744","https://openalex.org/W2973044449","https://openalex.org/W3015843733","https://openalex.org/W3042857426","https://openalex.org/W3046865219","https://openalex.org/W3094607766","https://openalex.org/W3095853290","https://openalex.org/W3099330747","https://openalex.org/W3104196160","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6696768431","https://openalex.org/W6711980375"],"related_works":["https://openalex.org/W2348192562","https://openalex.org/W2058482658","https://openalex.org/W1823208675","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W2073125797","https://openalex.org/W3135613579","https://openalex.org/W2037635165","https://openalex.org/W4200562864"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"an":[5,37,46,66],"efficient":[6],"end-to-end":[7],"neural":[8],"network":[9,64],"that":[10,96],"can":[11],"estimate":[12],"near-end":[13,59],"speech":[14,60,73],"using":[15],"a":[16],"U-convolution":[17,55],"block":[18,39],"by":[19],"exploiting":[20],"various":[21,104],"signals":[22],"to":[23,40,57,84],"achieve":[24],"residual":[25],"echo":[26,48],"suppression":[27],"(RES).":[28],"Specifically,":[29],"the":[30,54,69,77,97,101],"proposed":[31,63,98],"model":[32],"employs":[33],"multiple":[34],"encoders":[35],"and":[36,51,76,110],"integration":[38],"utilize":[41],"complete":[42],"signal":[43],"information":[44],"in":[45,68,86],"acoustic":[47],"cancellation":[49],"system":[50],"also":[52],"applies":[53],"blocks":[56],"separate":[58],"efficiently.":[61],"The":[62,92],"affords":[65],"improvement":[67],"perceptual":[70],"evaluation":[71],"of":[72,106],"quality":[74],"(PESQ)":[75],"short-time":[78],"objective":[79],"intelligibility":[80],"(STOI),":[81],"as":[82],"compared":[83],"baselines,":[85],"scenarios":[87],"involving":[88],"smart":[89],"audio":[90],"devices.":[91],"experimental":[93],"results":[94],"show":[95],"method":[99],"outperforms":[100],"baselines":[102],"for":[103],"types":[105],"mismatched":[107],"background":[108],"noise":[109],"environmental":[111],"reverberation,":[112],"while":[113],"requiring":[114],"low":[115],"computational":[116],"resources.":[117]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}