{"id":"https://openalex.org/W3014522660","doi":"https://doi.org/10.1109/icassp40776.2020.9053288","title":"Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement","display_name":"Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3014522660","doi":"https://doi.org/10.1109/icassp40776.2020.9053288","mag":"3014522660"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.13917","any_repository_has_fulltext":true},"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/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":"Chao-Han Yang","raw_affiliation_strings":["Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042520842","display_name":"Jun Qi","orcid":"https://orcid.org/0000-0001-7533-2630"},"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":"Jun Qi","raw_affiliation_strings":["Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050344371","display_name":"Pin\u2010Yu Chen","orcid":"https://orcid.org/0000-0003-1039-8369"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pin-Yu Chen","raw_affiliation_strings":["IBM Research, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001706958","display_name":"Xiaoli Ma","orcid":"https://orcid.org/0000-0002-3076-2589"},"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":"Xiaoli Ma","raw_affiliation_strings":["Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"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":"Chin-Hui Lee","raw_affiliation_strings":["Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3107","last_page":"3111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9911999702453613,"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":0.9503999948501587,"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/adversarial-system","display_name":"Adversarial system","score":0.810688316822052},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7557715177536011},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7106600999832153},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6376006007194519},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.6139903664588928},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5826698541641235},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49866342544555664},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4790267050266266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47737905383110046},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4431454837322235},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42637360095977783},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12018796801567078}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.810688316822052},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557715177536011},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7106600999832153},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6376006007194519},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.6139903664588928},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5826698541641235},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49866342544555664},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4790267050266266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47737905383110046},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4431454837322235},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42637360095977783},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12018796801567078},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053288","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.13917","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.13917","pdf_url":"https://arxiv.org/pdf/2003.13917","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.13917","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.13917","pdf_url":"https://arxiv.org/pdf/2003.13917","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.46000000834465027,"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":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W1922655562","https://openalex.org/W1945616565","https://openalex.org/W1983108229","https://openalex.org/W1987831012","https://openalex.org/W2044893557","https://openalex.org/W2067295501","https://openalex.org/W2078528584","https://openalex.org/W2746457594","https://openalex.org/W2770312844","https://openalex.org/W2774707525","https://openalex.org/W2782403400","https://openalex.org/W2892852825","https://openalex.org/W2898435086","https://openalex.org/W2902132730","https://openalex.org/W2923292931","https://openalex.org/W2952730822","https://openalex.org/W2962866211","https://openalex.org/W2963207607","https://openalex.org/W2963403868","https://openalex.org/W2963917611","https://openalex.org/W2964301649","https://openalex.org/W2964311653","https://openalex.org/W2969649301","https://openalex.org/W2970027712","https://openalex.org/W2973057252","https://openalex.org/W4232282348","https://openalex.org/W4289242435","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6640090968","https://openalex.org/W6640425456","https://openalex.org/W6739901393","https://openalex.org/W6746295503","https://openalex.org/W6746882984","https://openalex.org/W6746914816","https://openalex.org/W6754602573","https://openalex.org/W6756251360","https://openalex.org/W6760326341"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W1823208675","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W2546593254","https://openalex.org/W3135613579","https://openalex.org/W2037635165","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"highlighted":[3],"adversarial":[4,36,58,105,119,158,163,200],"examples":[5],"as":[6],"ubiquitous":[7],"threats":[8],"to":[9,34,80,88,96],"the":[10,42,52,56,71,99,112,130,137,145],"deep":[11],"neural":[12],"network":[13,132],"(DNN)":[14],"based":[15,26,141,150],"speech":[16,37,47,75,82,102,106,114],"recognition":[17,48,115],"systems.":[18],"In":[19],"this":[20],"work,":[21],"we":[22,40],"present":[23],"a":[24,205],"U-Net":[25,66],"attention":[27,131],"model,":[28],"UNet":[29],"<sub":[30,67],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[31,68],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">At</sub>":[32,69],",":[33],"enhance":[35],"signals.":[38],"Specifically,":[39],"evaluate":[41],"model":[43,53,152],"performance":[44,54],"by":[45,55,129,156],"interpretable":[46],"metrics":[49],"and":[50,184],"discuss":[51],"augmented":[57],"training.":[59],"Our":[60],"experiments":[61,110],"show":[62],"that":[63,124,173,195],"our":[64,196],"proposed":[65],"improves":[70],"perceptual":[72],"evaluation":[73],"of":[74,101,135,139,148],"quality":[76],"(PESQ)":[77],"from":[78,86,94],"1.13":[79],"2.78,":[81],"transmission":[83],"index":[84],"(STI)":[85],"0.65":[87],"0.75,":[89],"shortterm":[90],"objective":[91],"intelligibility":[92],"(STOI)":[93],"0.83":[95],"0.96":[97],"on":[98,111,169],"task":[100,117],"enhancement":[103,197],"with":[104,118,160,199],"examples.":[107],"We":[108,122],"conduct":[109],"automatic":[113],"(ASR)":[116],"audio":[120],"attacks.":[121],"find":[123],"(i)":[125],"temporal":[126],"features":[127],"learned":[128],"are":[133],"capable":[134],"enhancing":[136],"robustness":[138],"DNN":[140,149],"ASR":[142,151,167,207],"models;":[143],"(ii)":[144],"generalization":[146],"power":[147],"could":[153],"be":[154],"enhanced":[155],"applying":[157],"training":[159,201],"an":[161,176,185],"additive":[162],"data":[164],"augmentation.":[165],"The":[166],"metric":[168],"word-error-rates":[170],"(WERs)":[171],"shows":[172],"there":[174],"is":[175],"absolute":[177,186],"2.22":[178],"%":[179,188],"decrease":[180],"under":[181,190],"gradient-based":[182],"perturbation,":[183,192],"2.03":[187],"decrease,":[189],"evolutionary-optimized":[191],"which":[193],"suggests":[194],"models":[198],"can":[202],"further":[203],"secure":[204],"resilient":[206],"system.":[208]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}