{"id":"https://openalex.org/W4408355156","doi":"https://doi.org/10.1109/icassp49660.2025.10887835","title":"A Small-footprint Acoustic Echo Cancellation Solution for Mobile Full-Duplex Speech Interactions","display_name":"A Small-footprint Acoustic Echo Cancellation Solution for Mobile Full-Duplex Speech Interactions","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355156","doi":"https://doi.org/10.1109/icassp49660.2025.10887835"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5014118765","display_name":"Yiheng Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiheng Jiang","raw_affiliation_strings":["Alibaba Group,Speech Lab,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab,Beijing,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069657933","display_name":"Biao Tian","orcid":"https://orcid.org/0000-0001-7259-3739"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Tian","raw_affiliation_strings":["Alibaba Group,Speech Lab,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab,Beijing,China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014118765"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05588108,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9739999771118164,"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/echo","display_name":"Echo (communications protocol)","score":0.7702068090438843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6392993927001953},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5450783371925354},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5296580195426941},{"id":"https://openalex.org/keywords/duplex","display_name":"Duplex (building)","score":0.4757506549358368},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46020811796188354},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14847978949546814},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10226231813430786},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.06876233220100403}],"concepts":[{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.7702068090438843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6392993927001953},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5450783371925354},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5296580195426941},{"id":"https://openalex.org/C99611785","wikidata":"https://www.wikidata.org/wiki/Q6453233","display_name":"Duplex (building)","level":3,"score":0.4757506549358368},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46020811796188354},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14847978949546814},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10226231813430786},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.06876233220100403},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":29,"referenced_works":["https://openalex.org/W123803282","https://openalex.org/W1828123559","https://openalex.org/W1987040740","https://openalex.org/W2090210493","https://openalex.org/W2100471625","https://openalex.org/W2116983604","https://openalex.org/W2752143737","https://openalex.org/W2892110446","https://openalex.org/W2898268964","https://openalex.org/W2936774411","https://openalex.org/W2962892438","https://openalex.org/W2963308316","https://openalex.org/W3028077980","https://openalex.org/W3083531398","https://openalex.org/W3092864146","https://openalex.org/W3097906045","https://openalex.org/W3160394811","https://openalex.org/W3161761462","https://openalex.org/W3196995871","https://openalex.org/W3197704003","https://openalex.org/W3206246883","https://openalex.org/W4221155601","https://openalex.org/W4225269836","https://openalex.org/W4225299188","https://openalex.org/W4230577928","https://openalex.org/W4283067311","https://openalex.org/W4385823440","https://openalex.org/W4392903182","https://openalex.org/W4392903425"],"related_works":["https://openalex.org/W1473737476","https://openalex.org/W2949162897","https://openalex.org/W2061432289","https://openalex.org/W2276571074","https://openalex.org/W4300003799","https://openalex.org/W2158582019","https://openalex.org/W1500087777","https://openalex.org/W2368534554","https://openalex.org/W1970204757","https://openalex.org/W2148469257"],"abstract_inverted_index":{"In":[0],"full-duplex":[1],"speech":[2,69],"interaction":[3],"systems,":[4],"effective":[5],"Acoustic":[6],"Echo":[7,131],"Cancellation":[8],"(AEC)":[9],"is":[10,56],"crucial":[11],"for":[12,88],"recovering":[13],"echo-contaminated":[14],"speech.":[15],"This":[16],"paper":[17],"presents":[18],"a":[19,65,79,110],"neural":[20],"network-based":[21],"AEC":[22,61],"solution":[23],"to":[24,45,58],"address":[25],"challenges":[26],"in":[27,64,68,130,144],"mobile":[28,120],"scenarios":[29],"with":[30,113],"varying":[31],"hardware,":[32],"nonlinear":[33],"distortions":[34],"and":[35,96,135,147],"long":[36],"latency.":[37],"We":[38],"first":[39],"incorporate":[40],"diverse":[41],"data":[42],"augmentation":[43],"strategies":[44],"enhance":[46],"the":[47,127],"model\u2019s":[48],"robustness":[49],"across":[50],"various":[51],"environments.":[52],"Moreover,":[53],"progressive":[54],"learning":[55],"employed":[57],"incrementally":[59],"improve":[60],"effectiveness,":[62],"resulting":[63],"considerable":[66],"improvement":[67],"quality.":[70],"To":[71],"further":[72],"optimize":[73],"AEC\u2019s":[74],"downstream":[75],"applications,":[76],"we":[77],"introduce":[78],"novel":[80],"post-processing":[81],"strategy":[82],"employing":[83],"tailored":[84],"parameters":[85],"designed":[86],"specifically":[87],"tasks":[89],"such":[90],"as":[91],"Voice":[92],"Activity":[93],"Detection":[94],"(VAD)":[95],"Automatic":[97],"Speech":[98,139],"Recognition":[99],"(ASR),":[100],"thus":[101],"enhancing":[102],"their":[103],"overall":[104],"efficacy.":[105],"Finally,":[106],"our":[107],"method":[108,129],"employs":[109],"small-footprint":[111],"model":[112],"streaming":[114],"inference,":[115],"enabling":[116],"seamless":[117],"deployment":[118],"on":[119],"devices.":[121],"Empirical":[122],"results":[123],"demonstrate":[124],"effectiveness":[125],"of":[126,138],"proposed":[128],"Return":[132],"Loss":[133],"Enhancement":[134],"Perceptual":[136],"Evaluation":[137],"Quality,":[140],"alongside":[141],"significant":[142],"improvements":[143],"both":[145],"VAD":[146],"ASR":[148],"results.":[149]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
