{"id":"https://openalex.org/W4406462013","doi":"https://doi.org/10.1109/slt61566.2024.10832279","title":"SMRU: Split-And-Merge Recurrent-Based UNet For Acoustic Echo Cancellation And Noise Suppression","display_name":"SMRU: Split-And-Merge Recurrent-Based UNet For Acoustic Echo Cancellation And Noise Suppression","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406462013","doi":"https://doi.org/10.1109/slt61566.2024.10832279"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5018569990","display_name":"Zhihang Sun","orcid":"https://orcid.org/0000-0002-3787-0144"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihang Sun","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053757616","display_name":"Andong Li","orcid":"https://orcid.org/0000-0003-4094-8448"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andong Li","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073675630","display_name":"Rilin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rilin Chen","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397003","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0003-0877-2681"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407019","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0002-0031-9156"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005083930","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0001-7445-226X"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,School of Communications and Information Engineering,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,School of Communications and Information Engineering,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102835232","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-2874-5795"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5018569990"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.732466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"317","last_page":"324"},"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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.7080241441726685},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5841991305351257},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5373216271400452},{"id":"https://openalex.org/keywords/active-noise-control","display_name":"Active noise control","score":0.5261064171791077},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.4864523112773895},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4594297409057617},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.28855109214782715},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.21483728289604187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21398881077766418},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0831511914730072}],"concepts":[{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.7080241441726685},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5841991305351257},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5373216271400452},{"id":"https://openalex.org/C100342000","wikidata":"https://www.wikidata.org/wiki/Q583234","display_name":"Active noise control","level":3,"score":0.5261064171791077},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.4864523112773895},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4594297409057617},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.28855109214782715},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.21483728289604187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21398881077766418},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0831511914730072},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1973524311","https://openalex.org/W2032676419","https://openalex.org/W2168837669","https://openalex.org/W2696967604","https://openalex.org/W2804036797","https://openalex.org/W2952218014","https://openalex.org/W2963446712","https://openalex.org/W2973044449","https://openalex.org/W2991361823","https://openalex.org/W3099330747","https://openalex.org/W3158779859","https://openalex.org/W3160115460","https://openalex.org/W3188042919","https://openalex.org/W3197042120","https://openalex.org/W3197729725","https://openalex.org/W3203083806","https://openalex.org/W3205770165","https://openalex.org/W3206809722","https://openalex.org/W4221155601","https://openalex.org/W4224919230","https://openalex.org/W4224933775","https://openalex.org/W4224933821","https://openalex.org/W4312048186","https://openalex.org/W4312678820","https://openalex.org/W4372267082","https://openalex.org/W4385822305","https://openalex.org/W4385823327","https://openalex.org/W6796417832","https://openalex.org/W6847544085"],"related_works":["https://openalex.org/W1473737476","https://openalex.org/W2949162897","https://openalex.org/W2061432289","https://openalex.org/W2276571074","https://openalex.org/W4234886518","https://openalex.org/W2389591058","https://openalex.org/W2382112581","https://openalex.org/W3124036233","https://openalex.org/W4229787472","https://openalex.org/W2486541857"],"abstract_inverted_index":{"The":[0,64,140],"proliferation":[1],"of":[2,11,20,99,112,119,156],"deep":[3],"neural":[4],"networks":[5],"has":[6,177],"spawned":[7],"the":[8,34,94,100,122,132,159,164,178],"rapid":[9],"development":[10],"acoustic":[12],"echo":[13],"cancellation":[14],"and":[15,18,45,75,131,137,158,176],"noise":[16],"suppression,":[17],"plenty":[19],"prior":[21],"arts":[22],"have":[23],"been":[24],"proposed,":[25],"which":[26,120],"yield":[27],"promising":[28],"performance.":[29],"Nevertheless,":[30],"they":[31],"rarely":[32],"consider":[33],"deployment":[35],"generality":[36],"in":[37,67,154],"different":[38,61],"processing":[39],"scenarios,":[40],"such":[41],"as":[42],"edge":[43],"devices,":[44],"cloud":[46],"processing.":[47],"To":[48],"this":[49,51],"end,":[50],"paper":[52],"proposes":[53],"a":[54,70,104],"general":[55,185],"model,":[56],"termed":[57],"SMRU,":[58],"to":[59,81,149,181,183],"cover":[60],"application":[62],"scenarios.":[63],"novelty":[65],"lies":[66],"two-fold.":[68],"First,":[69],"multi-scale":[71],"band":[72,76],"split":[73],"layer":[74,78,126],"merge":[77],"are":[79],"proposed":[80,165],"effectively":[82],"fuse":[83],"local":[84],"frequency":[85],"bands":[86],"for":[87,135],"lower":[88],"complexity":[89,189],"modeling.":[90,139],"Besides,":[91],"by":[92],"simulating":[93],"multi-resolution":[95],"feature":[96],"modeling":[97],"characteristic":[98],"classical":[101],"UNet":[102,107],"structure,":[103],"novel":[105],"recurrent-dominated":[106],"is":[108,142],"devised.":[109],"It":[110],"consists":[111],"multiple":[113],"variable":[114],"frame":[115],"rate":[116],"blocks,":[117],"each":[118],"involves":[121],"causal":[123],"time":[124],"down-/upsampling":[125],"with":[127,187],"varying":[128,188],"compression":[129],"ratios":[130],"dualpath":[133],"structure":[134],"inter-":[136],"intra-band":[138],"model":[141],"configured":[143],"from":[144],"$50":[145],"\\mathrm{M}":[146],"/":[147,152],"\\mathrm{s}$":[148,153],"$6.8":[150],"\\mathrm{G}":[151],"terms":[155],"MACs,":[157],"experimental":[160],"results":[161],"show":[162],"that":[163],"approach":[166],"yields":[167],"competitive":[168],"or":[169],"even":[170],"better":[171],"performance":[172],"over":[173],"existing":[174],"baselines,":[175],"full":[179],"potential":[180],"adapt":[182],"more":[184],"scenarios":[186],"requirements.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}