{"id":"https://openalex.org/W3162646409","doi":"https://doi.org/10.1109/icassp39728.2021.9413585","title":"A Neural Acoustic Echo Canceller Optimized Using An Automatic Speech Recognizer and Large Scale Synthetic Data","display_name":"A Neural Acoustic Echo Canceller Optimized Using An Automatic Speech Recognizer and Large Scale Synthetic Data","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162646409","doi":"https://doi.org/10.1109/icassp39728.2021.9413585","mag":"3162646409"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413585","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":"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/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 Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","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 Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","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 Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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 Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"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":"Rohit Prabhavalkar","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7128","last_page":"7132"},"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8161813020706177},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7189213037490845},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.5852993130683899},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5292419791221619},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5077506303787231},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.48401567339897156},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45909127593040466},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43328866362571716},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4240800440311432},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4207567274570465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41375935077667236},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3663238286972046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8161813020706177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7189213037490845},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.5852993130683899},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5292419791221619},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5077506303787231},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.48401567339897156},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45909127593040466},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43328866362571716},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4240800440311432},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4207567274570465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41375935077667236},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3663238286972046},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413585","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W105949688","https://openalex.org/W123803282","https://openalex.org/W648786980","https://openalex.org/W1522301498","https://openalex.org/W1855892484","https://openalex.org/W2120847449","https://openalex.org/W2271840356","https://openalex.org/W2395657913","https://openalex.org/W2617258110","https://openalex.org/W2769810959","https://openalex.org/W2888860279","https://openalex.org/W2928941594","https://openalex.org/W2936774411","https://openalex.org/W2953932601","https://openalex.org/W2962760690","https://openalex.org/W2963782041","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2972461400","https://openalex.org/W2972970915","https://openalex.org/W3015194534","https://openalex.org/W3021469861","https://openalex.org/W3025715893","https://openalex.org/W3048487650","https://openalex.org/W3095173472","https://openalex.org/W3095853290","https://openalex.org/W4210409334","https://openalex.org/W4294619240","https://openalex.org/W6604264600","https://openalex.org/W6621543089","https://openalex.org/W6631190155","https://openalex.org/W6639156005","https://openalex.org/W6694517276","https://openalex.org/W6711980375","https://openalex.org/W6746700228","https://openalex.org/W6756319913","https://openalex.org/W6760633627","https://openalex.org/W6781924587"],"related_works":["https://openalex.org/W1473737476","https://openalex.org/W1974895211","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W2122233706","https://openalex.org/W642007152","https://openalex.org/W2105439218","https://openalex.org/W2131711534","https://openalex.org/W3143423642","https://openalex.org/W2341426843"],"abstract_inverted_index":{"We":[0],"consider":[1,73],"the":[2,69,82,98,148,154,168,185,190],"problem":[3],"of":[4,131],"recognizing":[5,21],"speech":[6,51,84,91],"utterances":[7],"spoken":[8],"to":[9,24,32,67,88,108,147,160],"a":[10,15,25,102,109,136,178],"device":[11],"which":[12,28,75],"is":[13,29,66,86],"generating":[14,30],"known":[16],"sound":[17],"waveform;":[18],"for":[19,46],"example,":[20],"queries":[22],"issued":[23],"digital":[26],"assistant":[27],"responses":[31],"previous":[33],"user":[34],"inputs.":[35],"Previous":[36],"work":[37],"has":[38],"proposed":[39,169,191],"building":[40],"acoustic":[41],"echo":[42],"cancellation":[43],"(AEC)":[44],"models":[45],"this":[47,116],"task":[48],"that":[49,104,115,126],"optimize":[50],"enhancement":[52],"metrics":[53],"using":[54],"both":[55],"neural":[56,186],"network":[57],"as":[58,60],"well":[59],"signal":[61,85,179],"processing":[62,180],"approaches.Since":[63],"our":[64,128],"goal":[65],"recognize":[68],"input":[70],"speech,":[71],"we":[72,96,124,166],"enhancements":[74],"improve":[76,171],"word":[77],"error":[78],"rates":[79],"(WERs)":[80],"when":[81],"predicted":[83],"passed":[87],"an":[89],"automatic":[90],"recognition":[92],"(ASR)":[93],"model.":[94],"First,":[95],"augment":[97],"loss":[99,118],"function":[100,119],"with":[101,135],"term":[103],"produces":[105],"outputs":[106],"useful":[107],"pre-trained":[110],"ASR":[111],"model":[112,155,188],"and":[113,182],"show":[114],"augmented":[117],"improves":[120,140],"WER":[121],"metrics.":[122],"Second,":[123],"demonstrate":[125],"augmenting":[127],"training":[129,152],"dataset":[130,139],"real":[132,161],"world":[133],"examples":[134],"large":[137],"synthetic":[138,159],"performance.":[141],"Crucially,":[142],"applying":[143],"SpecAugment":[144],"style":[145],"masks":[146],"reference":[149],"channel":[150],"during":[151],"aids":[153],"in":[156],"adapting":[157],"from":[158],"domains.":[162],"In":[163],"experimental":[164],"evaluations,":[165],"find":[167],"approaches":[170],"performance,":[172],"on":[173],"average,":[174],"by":[175],"57%":[176],"over":[177,184],"baseline":[181],"45%":[183],"AEC":[187],"without":[189],"changes.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}