{"id":"https://openalex.org/W4401114208","doi":"https://doi.org/10.1109/tsp63128.2024.10605922","title":"Synthetic Speech Detection Using Deep Neural Networks","display_name":"Synthetic Speech Detection Using Deep Neural Networks","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4401114208","doi":"https://doi.org/10.1109/tsp63128.2024.10605922"},"language":"en","primary_location":{"id":"doi:10.1109/tsp63128.2024.10605922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp63128.2024.10605922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 47th International Conference on Telecommunications and Signal Processing (TSP)","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/A5106106234","display_name":"Irina Mutica","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Irina Mutica","raw_affiliation_strings":["National University of Science and Technology POLITEHNICA,Speech and Dialogue Research Laboratory (SpeeD),Bucharest,Romania"],"affiliations":[{"raw_affiliation_string":"National University of Science and Technology POLITEHNICA,Speech and Dialogue Research Laboratory (SpeeD),Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020802166","display_name":"\u015eerban Mihalache","orcid":"https://orcid.org/0000-0001-6540-2359"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Serban Mihalache","raw_affiliation_strings":["National University of Science and Technology POLITEHNICA,Speech and Dialogue Research Laboratory (SpeeD),Bucharest,Romania"],"affiliations":[{"raw_affiliation_string":"National University of Science and Technology POLITEHNICA,Speech and Dialogue Research Laboratory (SpeeD),Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012068854","display_name":"Drago\u015f Burileanu","orcid":"https://orcid.org/0000-0002-7675-3506"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Dragos Burileanu","raw_affiliation_strings":["National University of Science and Technology POLITEHNICA,Speech and Dialogue Research Laboratory (SpeeD),Bucharest,Romania"],"affiliations":[{"raw_affiliation_string":"National University of Science and Technology POLITEHNICA,Speech and Dialogue Research Laboratory (SpeeD),Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5106106234"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":0.9948,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79771075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9556000232696533,"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":0.9556000232696533,"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":0.9472000002861023,"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":0.7124709486961365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5763219594955444},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5425636172294617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49861741065979004},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44555217027664185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124709486961365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5763219594955444},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5425636172294617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49861741065979004},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44555217027664185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsp63128.2024.10605922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp63128.2024.10605922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 47th International Conference on Telecommunications and Signal Processing (TSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2955425717","https://openalex.org/W2989571531","https://openalex.org/W2989851933","https://openalex.org/W3126967250","https://openalex.org/W3145444543","https://openalex.org/W3209628892","https://openalex.org/W4210381452","https://openalex.org/W4226246616","https://openalex.org/W4311599471","https://openalex.org/W4312743281","https://openalex.org/W4312758940","https://openalex.org/W4386302282"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"In":[0,45],"recent":[1],"years,":[2],"the":[3,87,97],"proliferation":[4],"of":[5,96,122,128],"synthetic":[6,33,51],"speech":[7,52,99],"has":[8],"raised":[9],"concerns":[10],"regarding":[11],"its":[12],"potential":[13],"misuse":[14],"for":[15,31,50],"unethical":[16],"activities":[17],"including":[18],"voice":[19],"impersonation":[20],"and":[21,71,78,102,124],"deep":[22,59],"fake":[23],"generation.":[24],"Addressing":[25],"this":[26,46],"challenge":[27],"requires":[28],"robust":[29],"methods":[30],"detecting":[32],"speech,":[34],"which":[35],"often":[36],"exhibits":[37],"subtle":[38],"but":[39],"discernible":[40],"differences":[41],"from":[42],"natural":[43],"speech.":[44],"paper,":[47],"three":[48],"approaches":[49],"detection":[53],"are":[54],"proposed,":[55],"two":[56],"based":[57,73],"on":[58,74,86,108],"neural":[60,68],"networks":[61,69],"(DNNs),":[62],"namely":[63],"multilayer":[64],"perceptrons":[65],"(MLPs),":[66],"convolutional":[67],"(CNNs),":[70],"one":[72],"an":[75],"EfficientNetV2":[76],"model":[77],"transfer":[79],"learning.":[80],"The":[81],"proposed":[82],"system":[83],"was":[84],"trained":[85],"Fake-or-Real":[88],"(FoR)":[89],"dataset,":[90],"comprising":[91],"utterances":[92],"generated":[93,111],"by":[94],"some":[95],"latest":[98],"synthesis":[100],"algorithms,":[101],"is":[103],"able":[104],"to":[105],"generalize":[106],"well":[107],"unseen":[109],"samples":[110],"with":[112],"algorithms":[113],"not":[114],"encountered":[115],"during":[116],"training,":[117],"yielding":[118],"a":[119,125],"validation":[120],"accuracy":[121,127],"98.9%":[123],"test":[126],"83.9%.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}