{"id":"https://openalex.org/W4297841228","doi":"https://doi.org/10.21437/interspeech.2022-10974","title":"A Conformer-based Waveform-domain Neural Acoustic Echo Canceller Optimized for ASR Accuracy","display_name":"A Conformer-based Waveform-domain Neural Acoustic Echo Canceller Optimized for ASR Accuracy","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841228","doi":"https://doi.org/10.21437/interspeech.2022-10974"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10974","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10974","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, U","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":true,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Google LLC, U"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, U","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, U","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101636869","display_name":"Shuai Shao","orcid":"https://orcid.org/0009-0002-7028-0944"},"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":"Shuai Shao","raw_affiliation_strings":["Google LLC, U"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, U","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060708515","display_name":"N. T. Howard","orcid":"https://orcid.org/0000-0002-8787-6309"},"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":"Nathan Howard","raw_affiliation_strings":["Google LLC, U"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, U","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111429885","display_name":"Alex Park","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":"Alex Park","raw_affiliation_strings":["Google LLC, U"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, U","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101759686","display_name":"James M. Walker","orcid":"https://orcid.org/0000-0002-4625-4175"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, U","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, U","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5000078382"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2538","last_page":"2542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9901999831199646,"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":0.9901999831199646,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9629999995231628,"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/waveform","display_name":"Waveform","score":0.7612954378128052},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.7087827920913696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5933616757392883},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.5575349926948547},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47258150577545166},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4518727958202362},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.44739025831222534},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4329933822154999},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3968963027000427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26430273056030273},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13048797845840454},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08711901307106018},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0777273178100586},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07565194368362427}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7612954378128052},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.7087827920913696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5933616757392883},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.5575349926948547},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47258150577545166},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4518727958202362},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.44739025831222534},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4329933822154999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3968963027000427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26430273056030273},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13048797845840454},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08711901307106018},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0777273178100586},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07565194368362427},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10974","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10974","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W105949688","https://openalex.org/W1494198834","https://openalex.org/W2617258110","https://openalex.org/W2888860279","https://openalex.org/W2928941594","https://openalex.org/W2936774411","https://openalex.org/W2953932601","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2972461400","https://openalex.org/W3015194534","https://openalex.org/W3015389285","https://openalex.org/W3095853290","https://openalex.org/W3096038883","https://openalex.org/W3097777922","https://openalex.org/W3160115460","https://openalex.org/W3160766462","https://openalex.org/W3162646409","https://openalex.org/W3170623612","https://openalex.org/W3172791765","https://openalex.org/W3197334355","https://openalex.org/W3203616181","https://openalex.org/W4225009879","https://openalex.org/W4225873749","https://openalex.org/W4226113028","https://openalex.org/W4226191785","https://openalex.org/W4300943593"],"related_works":["https://openalex.org/W2024367938","https://openalex.org/W2782295999","https://openalex.org/W1970292246","https://openalex.org/W2162306796","https://openalex.org/W2015118744","https://openalex.org/W4247952185","https://openalex.org/W1642462315","https://openalex.org/W2005619368","https://openalex.org/W1879092539","https://openalex.org/W2526155427"],"abstract_inverted_index":{"Acoustic":[0],"Echo":[1],"Cancellation":[2],"(AEC)":[3],"is":[4,17,73,108,158,167,174],"essential":[5],"for":[6,170],"accurate":[7],"recognition":[8],"of":[9],"queries":[10],"spoken":[11],"to":[12,147,160],"a":[13,25,52,61,86,90,99,104,135],"smart":[14],"speaker":[15],"that":[16,24,97],"playing":[18],"out":[19],"audio.Previous":[20],"work":[21],"has":[22],"shown":[23],"neural":[26,64,106,130,140,156],"AEC":[27,65,102,107,121,131,141],"model":[28,55,66,72,142,157],"operating":[29,150],"on":[30,85,151],"log-mel":[31],"spectral":[32],"features":[33],"(denoted":[34],"\"logmel\"":[35],"hereafter)":[36],"can":[37],"greatly":[38],"improve":[39],"Automatic":[40],"Speech":[41],"Recognition":[42],"(ASR)":[43],"accuracy":[44],"when":[45],"optimized":[46],"with":[47],"an":[48],"auxiliary":[49],"loss":[50],"utilizing":[51],"pre-trained":[53],"ASR":[54,83],"encoder.In":[56],"this":[57,123],"paper,":[58],"we":[59,95],"develop":[60],"conformer-based":[62],"waveform-domain":[63,105,129],"inspired":[67],"by":[68,75,143],"the":[69,119,126,154],"\"TasNet\"":[70],"architecture.The":[71],"trained":[74],"jointly":[76],"optimizing":[77],"Negative":[78],"Scale-Invariant":[79],"SNR":[80],"(SISNR)":[81],"and":[82,103,166],"losses":[84],"large":[87],"speech":[88],"dataset.On":[89],"realistic":[91],"rerecorded":[92],"test":[93,124],"set,":[94,125],"find":[96],"cascading":[98],"linear":[100,120],"adaptive":[101],"very":[109],"effective,":[110],"giving":[111],"56-59%":[112],"word":[113],"error":[114],"rate":[115],"(WER)":[116],"reduction":[117],"over":[118,134],"alone.On":[122],"1.6M":[127],"parameter":[128,138],"also":[132],"improves":[133],"larger":[136],"6.5M":[137],"logmeldomain":[139],"20-29%":[144],"in":[145],"easy":[146],"moderate":[148],"conditions.By":[149],"smaller":[152,164],"frames,":[153],"waveform":[155],"able":[159],"perform":[161],"better":[162,168],"at":[163],"sizes":[165],"suited":[169],"applications":[171],"where":[172],"memory":[173],"limited.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}