{"id":"https://openalex.org/W4388820588","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317404","title":"Adversarial Robustness of Mel Based Speaker Recognition Systems","display_name":"Adversarial Robustness of Mel Based Speaker Recognition Systems","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820588","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317404"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317404","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5060009643","display_name":"Ritu Srivastava","orcid":"https://orcid.org/0000-0002-5420-7627"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ritu Srivastava","raw_affiliation_strings":["CVIT, KCIS, IIIT,Hyderabad","CVIT, KCIS, IIIT, Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, KCIS, IIIT,Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"CVIT, KCIS, IIIT, Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041428713","display_name":"Saiteja Kosgi","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Saiteja Kosgi","raw_affiliation_strings":["CVIT, KCIS, IIIT,Hyderabad","CVIT, KCIS, IIIT, Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, KCIS, IIIT,Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"CVIT, KCIS, IIIT, Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082060797","display_name":"Sarath Sivaprasad","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sarath Sivaprasad","raw_affiliation_strings":["CVIT, KCIS, IIIT,Hyderabad","CVIT, KCIS, IIIT, Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, KCIS, IIIT,Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"CVIT, KCIS, IIIT, Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092418416","display_name":"Neha Sahipjohn","orcid":"https://orcid.org/0009-0009-1101-8701"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neha Sahipjohn","raw_affiliation_strings":["CVIT, KCIS, IIIT,Hyderabad","CVIT, KCIS, IIIT, Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, KCIS, IIIT,Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"CVIT, KCIS, IIIT, Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067298540","display_name":"Vineet Gandhi","orcid":"https://orcid.org/0000-0001-8861-7731"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vineet Gandhi","raw_affiliation_strings":["CVIT, KCIS, IIIT,Hyderabad","CVIT, KCIS, IIIT, Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CVIT, KCIS, IIIT,Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"CVIT, KCIS, IIIT, Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15043322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"145","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9973999857902527,"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":0.9973999857902527,"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":0.9682000279426575,"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":0.9467999935150146,"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/spectrogram","display_name":"Spectrogram","score":0.8399315476417542},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7988952994346619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7391255497932434},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.666536808013916},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6636989116668701},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5207428932189941},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4742909073829651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42939549684524536},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4080777168273926}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8399315476417542},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7988952994346619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7391255497932434},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.666536808013916},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6636989116668701},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5207428932189941},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4742909073829651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42939549684524536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4080777168273926},{"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},{"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:10.1109/apsipaasc58517.2023.10317404","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W67277430","https://openalex.org/W1494198834","https://openalex.org/W1945616565","https://openalex.org/W2103075368","https://openalex.org/W2114499274","https://openalex.org/W2176804518","https://openalex.org/W2183001115","https://openalex.org/W2726515241","https://openalex.org/W2765424254","https://openalex.org/W2767858146","https://openalex.org/W2794490148","https://openalex.org/W2889717020","https://openalex.org/W2890964092","https://openalex.org/W2894365374","https://openalex.org/W2910121883","https://openalex.org/W2936774411","https://openalex.org/W2938358845","https://openalex.org/W2970006822","https://openalex.org/W3007679772","https://openalex.org/W3094550259","https://openalex.org/W3095570773","https://openalex.org/W3100321043","https://openalex.org/W3103557498","https://openalex.org/W3153453329","https://openalex.org/W3155956353","https://openalex.org/W6640425456","https://openalex.org/W6686304833","https://openalex.org/W6745878906","https://openalex.org/W6750489868","https://openalex.org/W6767111847"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2502115930","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNN)":[3],"applied":[4],"to":[5,25,29,60,79,95,110,117,127],"Mel":[6,96],"spectrograms":[7],"now":[8],"have":[9],"a":[10,67,124],"dominant":[11],"presence":[12],"in":[13,85,164],"the":[14,53,73,86,102,129,140,146,153,165],"landscape":[15],"of":[16,52,75,81,104,145],"speaker":[17,42,77,84,149,155],"recognition":[18,150],"systems.":[19],"Correspondingly,":[20],"it":[21],"is":[22],"also":[23],"important":[24],"evaluate":[26],"their":[27],"robustness":[28],"adversarial":[30,62,92,130],"attacks":[31,93],"that":[32,66,80],"remains":[33],"not":[34],"thoroughly":[35],"explored":[36],"for":[37,41],"end-to-end":[38],"trained":[39],"CNNs":[40],"recognition.":[43],"Our":[44],"work":[45],"addresses":[46],"this":[47],"gap":[48],"and":[49,121,135,142],"investigates":[50],"variations":[51],"iterative":[54,69],"Fast":[55],"Gradient":[56],"Sign":[57],"Method":[58],"(FGSM)":[59],"perform":[61],"attacks.":[63],"We":[64],"observe":[65],"vanilla":[68],"FGSM":[70],"can":[71,157],"flip":[72],"identity":[74],"each":[76],"sample":[78],"every":[82],"other":[83],"LibriSpeech":[87],"dataset.":[88],"Furthermore,":[89],"we":[90,138],"propose":[91],"specific":[94,111],"spectrogram":[97],"features":[98],"by":[99],"(a)":[100],"limiting":[101],"number":[103],"pixels":[105],"attacked,":[106],"(b)":[107],"restricting":[108,115],"changes":[109,116,163],"frequency":[112],"bands,":[113],"(c)":[114],"particular":[118],"time":[119],"duration,":[120],"(d)":[122],"using":[123],"substitute":[125],"model":[126],"craft":[128],"sample.":[131],"Using":[132],"thorough":[133],"qualitative":[134],"quantitative":[136],"results,":[137],"demonstrate":[139],"fragility":[141],"non-intuitive":[143],"nature":[144],"current":[147],"CNN-based":[148],"systems,":[151],"where":[152],"predicted":[154],"identities":[156],"be":[158],"flipped":[159],"without":[160],"any":[161],"perceptible":[162],"audio.":[166],"The":[167],"samples":[168],"are":[169],"available":[170],"at":[171],"\"https://advdemo.github.io/speech/\"":[172]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}