{"id":"https://openalex.org/W4392903182","doi":"https://doi.org/10.1109/icassp48485.2024.10447477","title":"Improving Acoustic Echo Cancellation for Voice Assistants Using Neural Echo Suppression and Multi-Microphone Noise Reduction","display_name":"Improving Acoustic Echo Cancellation for Voice Assistants Using Neural Echo Suppression and Multi-Microphone Noise Reduction","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903182","doi":"https://doi.org/10.1109/icassp48485.2024.10447477"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5021547071","display_name":"Jens Heitkaemper","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jens Heitkaemper","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075831886","display_name":"Turaj Zakizadeh Shabestary","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Turaj Zakizadeh Shabestary","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062398886","display_name":"Sankaran Panchapagesan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sankaran Panchapagesan","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101759687","display_name":"James M. Walker","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Walker","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094178912","display_name":"Bhalchandra Gajare","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhalchandra Gajare","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094178913","display_name":"Shlomi Regev","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomi Regev","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094178914","display_name":"Ajay Dudani","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajay Dudani","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012096308","display_name":"Alexander Gruenstein","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Gruenstein","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5021547071"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.3768,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4949403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"736","last_page":"740"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983999729156494,"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/microphone","display_name":"Microphone","score":0.8333792686462402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.737554669380188},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.6878618001937866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6753448247909546},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5880519151687622},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.549971342086792},{"id":"https://openalex.org/keywords/adaptive-filter","display_name":"Adaptive filter","score":0.4571826457977295},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4401141405105591},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4344692826271057},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.413188099861145},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2949145436286926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24788326025009155},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1653519570827484},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09511429071426392},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07398316264152527}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.8333792686462402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737554669380188},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.6878618001937866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6753448247909546},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5880519151687622},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.549971342086792},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.4571826457977295},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4401141405105591},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4344692826271057},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.413188099861145},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2949145436286926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24788326025009155},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1653519570827484},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09511429071426392},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07398316264152527},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W105949688","https://openalex.org/W1494198834","https://openalex.org/W1597121597","https://openalex.org/W2156676906","https://openalex.org/W2891296906","https://openalex.org/W2891997645","https://openalex.org/W2902557749","https://openalex.org/W2928941594","https://openalex.org/W2937769560","https://openalex.org/W2962935966","https://openalex.org/W2963977978","https://openalex.org/W2964058413","https://openalex.org/W2972402291","https://openalex.org/W2995181338","https://openalex.org/W3015843733","https://openalex.org/W3083531398","https://openalex.org/W3097777922","https://openalex.org/W3160766462","https://openalex.org/W3162646409","https://openalex.org/W3197704003","https://openalex.org/W3198436545","https://openalex.org/W3198442913","https://openalex.org/W4285820097","https://openalex.org/W4297841228","https://openalex.org/W4297841744","https://openalex.org/W4297841782","https://openalex.org/W4297841802","https://openalex.org/W4319862721","https://openalex.org/W4372266577","https://openalex.org/W4372346318","https://openalex.org/W4379033950","https://openalex.org/W4385807454","https://openalex.org/W6760633627"],"related_works":["https://openalex.org/W2738771020","https://openalex.org/W1607021895","https://openalex.org/W2733029664","https://openalex.org/W2801062816","https://openalex.org/W2954392969","https://openalex.org/W2162631815","https://openalex.org/W3124166275","https://openalex.org/W2026859618","https://openalex.org/W812148123","https://openalex.org/W2103984789"],"abstract_inverted_index":{"Keyword":[0],"spotting":[1],"(KS)":[2],"and":[3,54,158,181],"automatic":[4],"speech":[5],"recognition":[6],"(ASR)":[7],"on":[8],"smart":[9],"speakers":[10],"in":[11,28,100,152,162],"a":[12,41,55,103,127],"home":[13],"environment":[14],"with":[15,60,109],"interfering":[16],"signals":[17],"from":[18,81],"loudspeakers":[19],"are":[20],"challenging":[21],"tasks":[22],"to":[23,39,79,84],"this":[24,35],"day,":[25],"despite":[26],"improvements":[27],"acoustic":[29],"echo":[30,57],"cancellation":[31],"(AEC)":[32],"systems.":[33],"In":[34],"work":[36],"we":[37,112],"propose":[38],"combine":[40],"single":[42,89,145],"microphone":[43,90,146],"AEC":[44,77,118],"system,":[45],"consisting":[46],"of":[47],"an":[48,61,177,185],"adaptive":[49,62],"linear":[50,117],"filter":[51,63],"(linear":[52],"AEC)":[53],"neural":[56],"suppressor":[58],"(NES),":[59],"developed":[64],"for":[65,144],"multi-microphone":[66,170],"noise":[67],"reduction,":[68],"called":[69],"Cleaner.":[70],"This":[71],"additional":[72,178,186],"enhancement":[73],"step":[74],"allows":[75],"the":[76,95,131,136,140,169,172,182],"system":[78,138],"profit":[80],"spatial":[82],"information":[83],"remove":[85],"residual":[86],"echo.":[87],"The":[88],"NES":[91],"model":[92,121,142],"improves":[93],"upon":[94],"waveform":[96],"domain":[97,105],"counterpart":[98],"proposed":[99,137],"[1]":[101,143],"using":[102,115],"frequency":[104],"representation":[106],"that":[107,114],"helps":[108],"generalization.":[110],"Furthermore,":[111],"show":[113],"multiple":[116],"configurations":[119],"during":[120],"training":[122],"provides":[123],"large":[124],"gains":[125],"over":[126],"fixed":[128],"configuration.":[129],"On":[130],"hardest":[132],"considered":[133],"test":[134],"condition,":[135],"outperforms":[139],"baseline":[141],"input":[147],"by":[148,176,184],"66":[149],"%":[150,160,180],"(relative)":[151,161],"KS":[153],"false":[154],"reject":[155],"rate":[156,166],"(FRR)":[157],"52":[159,179],"ASR":[163],"word":[164],"error":[165],"(WER).":[167],"Using":[168],"setting,":[171],"FRR":[173],"is":[174],"reduced":[175],"WER":[183],"32":[187],"%.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}