{"id":"https://openalex.org/W2602814339","doi":"https://doi.org/10.1109/jstsp.2017.2684705","title":"Spectral Features for Synthetic Speech Detection","display_name":"Spectral Features for Synthetic Speech Detection","publication_year":2017,"publication_date":"2017-03-20","ids":{"openalex":"https://openalex.org/W2602814339","doi":"https://doi.org/10.1109/jstsp.2017.2684705","mag":"2602814339"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2017.2684705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2684705","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5041343074","display_name":"Dipjyoti Paul","orcid":"https://orcid.org/0000-0002-5320-1602"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Dipjyoti Paul","raw_affiliation_strings":["Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586349","display_name":"Monisankha Pal","orcid":"https://orcid.org/0000-0002-8234-0222"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Monisankha Pal","raw_affiliation_strings":["Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069790572","display_name":"Goutam Saha","orcid":"https://orcid.org/0000-0001-6187-1684"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Goutam Saha","raw_affiliation_strings":["Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041343074"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":5.8585,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.96780171,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"11","issue":"4","first_page":"605","last_page":"617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"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":0.7997016906738281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7299002408981323},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.7086631059646606},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5848429799079895},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5793192982673645},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5646818280220032},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5397947430610657},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.48614856600761414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4667527973651886},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4651198387145996},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.43882277607917786},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4273463189601898},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41748321056365967},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38738250732421875},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3044886589050293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997016906738281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7299002408981323},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.7086631059646606},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5848429799079895},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5793192982673645},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5646818280220032},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5397947430610657},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.48614856600761414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4667527973651886},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4651198387145996},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.43882277607917786},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4273463189601898},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41748321056365967},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38738250732421875},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3044886589050293},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2017.2684705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2684705","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6800000071525574,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W11511395","https://openalex.org/W282499614","https://openalex.org/W1490120479","https://openalex.org/W1507099578","https://openalex.org/W2014485509","https://openalex.org/W2041823554","https://openalex.org/W2047346462","https://openalex.org/W2062826588","https://openalex.org/W2064463502","https://openalex.org/W2072473772","https://openalex.org/W2077740952","https://openalex.org/W2117544888","https://openalex.org/W2123299109","https://openalex.org/W2137075158","https://openalex.org/W2138878452","https://openalex.org/W2143076824","https://openalex.org/W2144404214","https://openalex.org/W2147145909","https://openalex.org/W2148154194","https://openalex.org/W2150008717","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2156142001","https://openalex.org/W2165308841","https://openalex.org/W2165880886","https://openalex.org/W2168254078","https://openalex.org/W2176804518","https://openalex.org/W2186111442","https://openalex.org/W2186774823","https://openalex.org/W2290028669","https://openalex.org/W2294013337","https://openalex.org/W2295518531","https://openalex.org/W2295634712","https://openalex.org/W2296529392","https://openalex.org/W2301040327","https://openalex.org/W2394783243","https://openalex.org/W2395116999","https://openalex.org/W2398758564","https://openalex.org/W2401315748","https://openalex.org/W2403139431","https://openalex.org/W2405506115","https://openalex.org/W2406845569","https://openalex.org/W2407170210","https://openalex.org/W2407427462","https://openalex.org/W2428180336","https://openalex.org/W2511192463","https://openalex.org/W2511547178","https://openalex.org/W2513054450","https://openalex.org/W2517801484","https://openalex.org/W2533075636","https://openalex.org/W2548055032","https://openalex.org/W2686310949","https://openalex.org/W3198123200","https://openalex.org/W6600449757","https://openalex.org/W6629265402","https://openalex.org/W6630429238","https://openalex.org/W6681278112","https://openalex.org/W6685748340","https://openalex.org/W6686645966","https://openalex.org/W6696494075","https://openalex.org/W6697168226","https://openalex.org/W6697322189","https://openalex.org/W6712270117","https://openalex.org/W6712883666","https://openalex.org/W6713361921","https://openalex.org/W6713385238","https://openalex.org/W6713566751","https://openalex.org/W6713679595","https://openalex.org/W6713808294","https://openalex.org/W6729633544","https://openalex.org/W7064215089"],"related_works":["https://openalex.org/W2547760228","https://openalex.org/W2836844603","https://openalex.org/W3173366380","https://openalex.org/W2766680336","https://openalex.org/W2133320490","https://openalex.org/W4289830142","https://openalex.org/W3150393935","https://openalex.org/W1497065097","https://openalex.org/W2125446021","https://openalex.org/W2980055100"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,24,28,105],"voice":[3],"conversion":[4],"(VC)":[5],"and":[6,31,53,82,112,139,165,204,227],"speech":[7,49,52,128,226,240],"synthesis":[8],"research":[9],"make":[10],"speech-based":[11],"biometric":[12],"systems":[13,30],"highly":[14],"prone":[15],"to":[16,34,102],"spoofing":[17,37,242],"attacks.":[18,38,206],"This":[19],"can":[20,64],"provoke":[21],"an":[22],"increase":[23],"false":[25],"acceptance":[26],"rate":[27,211],"such":[29,36],"requires":[32],"countermeasure":[33],"mitigate":[35],"In":[39],"this":[40],"paper,":[41],"we":[42],"first":[43],"study":[44,92],"the":[45,67,103,106,116,190,194,228,237],"characteristics":[46],"of":[47,58,86,97,179,213,231],"synthetic":[48,127,180],"vis-\u00e0-vis":[50],"natural":[51,239],"then":[54],"propose":[55],"a":[56,94,133,136],"set":[57],"novel":[59],"short-term":[60],"spectral":[61,199],"features":[62,74,196,200],"that":[63,189,221],"efficiently":[65],"capture":[66],"discriminative":[68],"information":[69],"between":[70],"them.":[71],"The":[72,171,186],"proposed":[73,195],"are":[75,155,167,173],"computed":[76],"using":[77],"inverted":[78,110],"frequency":[79,111],"warping":[80,107],"scale":[81,108],"overlapped":[83],"block":[84,113,117],"transformation":[85],"filter":[87],"bank":[88],"log":[89],"energies.":[90],"Our":[91],"presents":[93],"detailed":[95],"analysis":[96],"antispoofing":[98],"performance":[99,120,230],"with":[100,142,161],"respect":[101],"variations":[104],"for":[109,115,201,218],"size":[114],"transform.":[118],"For":[119,148],"analysis,":[121],"Gaussian":[122],"mixture":[123],"model":[124,164],"(GMM)":[125],"based":[126,192],"detector":[129],"is":[130,234],"used":[131,156,168],"as":[132,157,169],"classifier":[134],"on":[135,175,193],"stand-alone":[137],"basis":[138],"also,":[140],"integrated":[141],"automatic":[143],"speaker":[144],"verification":[145],"(ASV)":[146],"systems.":[147],"ASV":[149],"systems,":[150],"standard":[151],"mel-frequency":[152],"cepstral":[153],"coefficients":[154],"feature":[158],"while":[159],"GMM":[160],"universal":[162],"background":[163],"i-vector":[166],"classifiers.":[170],"experiments":[172],"conducted":[174],"ten":[176],"different":[177],"kinds":[178],"data":[181],"from":[182],"ASVspoof":[183],"2015":[184],"corpus.":[185],"results":[187],"show":[188],"countermeasures":[191],"outperform":[197],"other":[198],"both":[202],"known":[203],"unknown":[205],"An":[207],"average":[208],"equal":[209],"error":[210],"(EER)":[212],"0.00%":[214],"has":[215],"been":[216],"achieved":[217],"nine":[219],"attacks":[220],"use":[222],"VC":[223],"or":[224],"SS":[225],"best":[229],"7.12%":[232],"EER":[233],"arrived":[235],"at":[236],"remaining":[238],"concatenation-based":[241],"attack.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}