{"id":"https://openalex.org/W4297841672","doi":"https://doi.org/10.21437/interspeech.2022-11361","title":"Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning","display_name":"Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841672","doi":"https://doi.org/10.21437/interspeech.2022-11361"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11361","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11361","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/A5036502813","display_name":"Nilaksh Das","orcid":"https://orcid.org/0000-0002-5281-5549"},"institutions":[{"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":"Nilaksh Das","raw_affiliation_strings":["Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102322734","display_name":"Polo Chau","orcid":null},"institutions":[{"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":false,"raw_author_name":"Polo Chau","raw_affiliation_strings":["Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5036502813"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11159205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3839","last_page":"3843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9821000099182129,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9593999981880188,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/robustness","display_name":"Robustness (evolution)","score":0.7759750485420227},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7732267379760742},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686458826065063},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6626781225204468},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5292707681655884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4999659061431885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3463597297668457},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14109107851982117}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7759750485420227},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7732267379760742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686458826065063},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6626781225204468},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5292707681655884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4999659061431885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3463597297668457},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14109107851982117},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11361","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11361","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2133564696","https://openalex.org/W2766219058","https://openalex.org/W2782403400","https://openalex.org/W2889494795","https://openalex.org/W2891267443","https://openalex.org/W2962684181","https://openalex.org/W2962717526","https://openalex.org/W2962780374","https://openalex.org/W2963161670","https://openalex.org/W2963821905","https://openalex.org/W2964301649","https://openalex.org/W2973252307","https://openalex.org/W2983044655","https://openalex.org/W3014522660","https://openalex.org/W3088377098","https://openalex.org/W3097777922","https://openalex.org/W3107485598","https://openalex.org/W3162037819","https://openalex.org/W3167895882","https://openalex.org/W3177907654","https://openalex.org/W3180992661","https://openalex.org/W3197285286","https://openalex.org/W3205419997","https://openalex.org/W3208456187","https://openalex.org/W4287250127","https://openalex.org/W4287282771","https://openalex.org/W4288359148","https://openalex.org/W4293846201","https://openalex.org/W4300434632"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"As":[0],"automatic":[1],"speech":[2,74],"recognition":[3],"(ASR)":[4],"systems":[5],"are":[6],"now":[7],"being":[8],"widely":[9],"deployed":[10],"in":[11,41,49,72,121,148],"the":[12,14,24,32,50,58,66,73,123,136,169],"wild,":[13],"increasing":[15],"threat":[16],"of":[17,28,60,69,96,138],"adversarial":[18,47,67,97,115,175],"attacks":[19,48],"raises":[20],"serious":[21,124],"questions":[22],"about":[23],"security":[25],"and":[26,89,91,126,165],"reliability":[27],"using":[29],"such":[30,62,85],"systems.On":[31],"other":[33],"hand,":[34],"multi-task":[35,63,179],"learning":[36,64,161,180],"(MTL)":[37],"has":[38],"shown":[39],"success":[40],"training":[42],"models":[43,71],"that":[44,102,130,173],"can":[45],"resist":[46],"computer":[51],"vision":[52],"domain.In":[53],"this":[54],"work,":[55],"we":[56],"investigate":[57],"impact":[59,134],"performing":[61,103],"on":[65,135],"robustness":[68,137,176],"ASR":[70],"domain.We":[75],"conduct":[76],"extensive":[77],"MTL":[78,104,139,142],"experimentation":[79],"by":[80],"combining":[81],"semantically":[82,106],"diverse":[83,107],"tasks":[84,108],"as":[86],"accent":[87],"classification":[88],"ASR,":[90],"evaluate":[92],"a":[93,132],"wide":[94],"range":[95],"settings.Our":[98],"thorough":[99],"analysis":[100],"reveals":[101],"with":[105],"consistently":[109],"makes":[110],"it":[111],"harder":[112],"for":[113,181],"an":[114],"attack":[116],"to":[117,156,159],"succeed.We":[118],"also":[119],"discuss":[120],"detail":[122],"pitfalls":[125],"their":[127],"related":[128],"remedies":[129],"have":[131],"significant":[133],"models.Our":[140],"proposed":[141],"approach":[143],"shows":[144],"considerable":[145],"absolute":[146],"improvements":[147],"adversarially":[149],"targeted":[150],"WER":[151],"ranging":[152],"from":[153,178],"17.25":[154],"up":[155],"59.90":[157],"compared":[158],"single-task":[160],"baselines":[162],"(attention":[163],"decoder":[164],"CTC":[166],"respectively).Ours":[167],"is":[168],"first":[170],"in-depth":[171],"study":[172],"uncovers":[174],"gains":[177],"ASR.":[182]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}