{"id":"https://openalex.org/W4225262970","doi":"https://doi.org/10.1109/icassp43922.2022.9746230","title":"Mitigating Closed-Model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition","display_name":"Mitigating Closed-Model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225262970","doi":"https://doi.org/10.1109/icassp43922.2022.9746230"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746230","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["Amazon Alexa AI,USA","Georgia Institute of Technology, USA","Amazon Alexa AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101468572","display_name":"Zeeshan Ahmed","orcid":"https://orcid.org/0009-0005-8514-9625"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeeshan Ahmed","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022646825","display_name":"Yile Gu","orcid":"https://orcid.org/0000-0003-3662-5056"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yile Gu","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072368204","display_name":"Joseph Szurley","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Szurley","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076628167","display_name":"Roger Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roger Ren","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031896207","display_name":"Linda Liu","orcid":"https://orcid.org/0000-0003-3687-9291"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linda Liu","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109934165","display_name":"Ivan Bulyko","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Bulyko","raw_affiliation_strings":["Amazon Alexa AI,USA","Amazon Alexa AI, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa AI, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5020376803"],"corresponding_institution_ids":["https://openalex.org/I130701444","https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.3118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47769877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"32","issue":null,"first_page":"6302","last_page":"6306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9950000047683716,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9904000163078308,"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/computer-science","display_name":"Computer science","score":0.7674513459205627},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7040051221847534},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.610663890838623},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5305994749069214},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5253103375434875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48613402247428894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4807686507701874},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.46667587757110596},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4615931510925293},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4316108822822571},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4253905415534973},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32037845253944397},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31572282314300537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674513459205627},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7040051221847534},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.610663890838623},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5305994749069214},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5253103375434875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48613402247428894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4807686507701874},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.46667587757110596},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4615931510925293},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4316108822822571},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4253905415534973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32037845253944397},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31572282314300537},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746230","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1922655562","https://openalex.org/W1945616565","https://openalex.org/W2075815989","https://openalex.org/W2093554785","https://openalex.org/W2127141656","https://openalex.org/W2164411961","https://openalex.org/W2171830216","https://openalex.org/W2407420912","https://openalex.org/W2746600820","https://openalex.org/W2785606994","https://openalex.org/W2892852825","https://openalex.org/W2895033754","https://openalex.org/W2898435086","https://openalex.org/W2904530326","https://openalex.org/W2913848079","https://openalex.org/W2935726938","https://openalex.org/W2962065000","https://openalex.org/W2962711307","https://openalex.org/W2962756933","https://openalex.org/W2963917611","https://openalex.org/W2964205597","https://openalex.org/W2964301649","https://openalex.org/W2964334477","https://openalex.org/W2973057252","https://openalex.org/W3014522660","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3103340107","https://openalex.org/W3106412272","https://openalex.org/W3150987417","https://openalex.org/W3173081491","https://openalex.org/W3198781161","https://openalex.org/W4226316089","https://openalex.org/W4287250127","https://openalex.org/W4293846201","https://openalex.org/W4392181513","https://openalex.org/W6631362777","https://openalex.org/W6640090968","https://openalex.org/W6640425456","https://openalex.org/W6684488266","https://openalex.org/W6739868092","https://openalex.org/W6747657013","https://openalex.org/W6748458661","https://openalex.org/W6754602573","https://openalex.org/W6754762128","https://openalex.org/W6757074599","https://openalex.org/W6758975236","https://openalex.org/W6765966558","https://openalex.org/W6774549192","https://openalex.org/W6780218876","https://openalex.org/W6795825774"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372","https://openalex.org/W2113211312"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,109],"aim":[4],"to":[5,115,119,129,135],"enhance":[6],"the":[7,103,123,136,142],"system":[8],"robustness":[9],"of":[10,54,88],"end-to-end":[11],"automatic":[12],"speech":[13,18,144],"recognition":[14],"(ASR)":[15],"against":[16,76,141],"adversarially-noisy":[17],"examples.":[19,145],"We":[20,60,83],"focus":[21],"on":[22,131],"a":[23,55],"rigorous":[24],"and":[25,47,92,121],"empirical":[26],"\"closed-model":[27],"adversarial":[28,37,69,78,99,143],"robustness\"":[29],"setting":[30],"(e.g.,":[31,45],"on-device":[32],"or":[33],"cloud":[34],"applications).":[35],"The":[36],"noise":[38],"is":[39],"only":[40],"generated":[41],"by":[42,113,127],"closed-model":[43],"optimization":[44],"evolutionary":[46],"zeroth-order":[48],"estimation)":[49],"without":[50],"accessing":[51],"gradient":[52],"information":[53],"targeted":[56],"ASR":[57,95],"model":[58,73,138],"directly.":[59],"propose":[61],"an":[62],"advanced":[63],"Bayesian":[64],"neural":[65],"network":[66],"(BNN)":[67],"based":[68,94,106],"detector,":[70],"which":[71],"could":[72],"latent":[74],"distributions":[75],"adaptive":[77],"perturbation":[79],"with":[80,97],"divergence":[81],"measurement.":[82],"further":[84],"simulate":[85],"deployment":[86],"scenarios":[87],"RNN":[89],"Transducer,":[90],"Conformer,":[91],"wav2vec-2.0":[93],"systems":[96],"proposed":[98,104],"detection":[100,107,111],"system.":[101],"Leveraging":[102],"BNN":[105],"system,":[108],"improve":[110],"rate":[112,126],"+2.77":[114],"+5.42%":[116],"(relative":[117],"+3.03":[118],"+6.26%)":[120],"reduce":[122],"word":[124],"error":[125],"5.02":[128],"7.47%":[130],"LibriSpeech":[132],"datasets":[133],"compared":[134],"current":[137],"enhancement":[139],"methods":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}