{"id":"https://openalex.org/W3170179936","doi":"https://doi.org/10.1109/lsp.2021.3089437","title":"Towards End-to-End Synthetic Speech Detection","display_name":"Towards End-to-End Synthetic Speech Detection","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3170179936","doi":"https://doi.org/10.1109/lsp.2021.3089437","mag":"3170179936"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2021.3089437","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3089437","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.06341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Guang Hua","orcid":"https://orcid.org/0000-0001-5184-4359"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Hua","raw_affiliation_strings":["School of Electronic Information, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-5184-4359","affiliations":[{"raw_affiliation_string":"School of Electronic Information, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andrew Beng Jin Teoh","orcid":"https://orcid.org/0000-0001-5063-9484"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Andrew Beng Jin Teoh","raw_affiliation_strings":["School of Electrical and Electronic Engineering, College of Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-5063-9484","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, College of Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":null,"display_name":"Haijian Zhang","orcid":"https://orcid.org/0000-0001-8314-6563"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijian Zhang","raw_affiliation_strings":["School of Electronic Information, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-8314-6563","affiliations":[{"raw_affiliation_string":"School of Electronic Information, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.2451,"has_fulltext":false,"cited_by_count":171,"citation_normalized_percentile":{"value":0.99502272,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"1265","last_page":"1269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9312000274658203,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9312000274658203,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.054499998688697815,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6208000183105469},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.5882999897003174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5748000144958496},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5702000260353088},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5357000231742859},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5139999985694885},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46230000257492065},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45680001378059387},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4514000117778778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253000140190125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6251000165939331},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6208000183105469},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5882999897003174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5702000260353088},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5042999982833862},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46230000257492065},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4311999976634979},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4171999990940094},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.3831999897956848},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.3301999866962433},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.3280999958515167},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2685999870300293}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2021.3089437","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3089437","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2106.06341","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.06341","pdf_url":"https://arxiv.org/pdf/2106.06341","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2106.06341","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.06341","pdf_url":"https://arxiv.org/pdf/2106.06341","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2014485509","https://openalex.org/W2097117768","https://openalex.org/W2111284386","https://openalex.org/W2464759814","https://openalex.org/W2533075636","https://openalex.org/W2567375321","https://openalex.org/W2572432338","https://openalex.org/W2576165910","https://openalex.org/W2590129515","https://openalex.org/W2596411757","https://openalex.org/W2602814339","https://openalex.org/W2602887606","https://openalex.org/W2606361731","https://openalex.org/W2686310949","https://openalex.org/W2733416080","https://openalex.org/W2738359832","https://openalex.org/W2740489634","https://openalex.org/W2747872086","https://openalex.org/W2763881998","https://openalex.org/W2772315375","https://openalex.org/W2907398704","https://openalex.org/W2936802426","https://openalex.org/W2952218014","https://openalex.org/W2964135678","https://openalex.org/W2972465261","https://openalex.org/W2972703466","https://openalex.org/W2972717745","https://openalex.org/W2973164265","https://openalex.org/W2973181078","https://openalex.org/W2979373447","https://openalex.org/W2990833974","https://openalex.org/W3015420010","https://openalex.org/W3024850948","https://openalex.org/W3026777299","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6685748340","https://openalex.org/W6687483927","https://openalex.org/W6696085341","https://openalex.org/W6697322189","https://openalex.org/W6745136726","https://openalex.org/W6761114050","https://openalex.org/W6778823374","https://openalex.org/W6784620459"],"related_works":["https://openalex.org/W2794438528","https://openalex.org/W2110108310","https://openalex.org/W3015853838","https://openalex.org/W3094189801","https://openalex.org/W2536333783","https://openalex.org/W642007152","https://openalex.org/W596245619","https://openalex.org/W3126967250","https://openalex.org/W2174199565","https://openalex.org/W2989279302"],"abstract_inverted_index":{"The":[0,102],"constant":[1,28],"Q":[2,29],"transform":[3],"(CQT)":[4],"has":[5],"been":[6],"shown":[7],"to":[8,18],"be":[9,74],"one":[10],"of":[11,157],"the":[12,54,67,95,99,122,147,154],"most":[13],"effective":[14],"speech":[15,21,162],"signal":[16],"pre-transforms":[17],"facilitate":[19],"synthetic":[20,161],"detection,":[22,163],"followed":[23],"by":[24,76,84],"either":[25],"hand-crafted":[26,70,165],"(subband)":[27],"cepstral":[30],"coefficient":[31],"(CQCC)":[32],"feature":[33,49],"extraction":[34,50],"and":[35,51,69],"a":[36,41,59,89],"back-end":[37],"binary":[38],"classifier,":[39],"or":[40,115],"deep":[42],"neural":[43,91],"network":[44,92],"(DNN)":[45],"directly":[46],"for":[47,98,160],"further":[48,119],"classification.":[52],"Despite":[53],"rich":[55],"literature":[56],"on":[57,131,141],"such":[58],"pipeline,":[60],"we":[61,80],"show":[62],"in":[63],"this":[64],"paper":[65,152],"that":[66,83,121],"pre-transform":[68],"features":[71],"could":[72,93,134],"simply":[73],"replaced":[75],"end-to-end":[77,158],"DNNs.":[78],"Specifically,":[79],"experimentally":[81],"verify":[82],"only":[85],"using":[86],"standard":[87],"components,":[88],"light-weight":[90],"outperform":[94],"state-of-the-art":[96],"methods":[97],"ASVspoof2019":[100],"challenge.":[101],"proposed":[103,123],"model":[104],"is":[105],"termed":[106],"Time-domain":[107],"Synthetic":[108],"Speech":[109],"Detection":[110],"Net":[111],"(TSSDNet),":[112],"having":[113],"ResNet-":[114],"Inception-style":[116],"structures.":[117],"We":[118],"demonstrate":[120],"models":[124],"also":[125],"have":[126],"attractive":[127],"generalization":[128],"capability.":[129],"Trained":[130],"ASVspoof2019,":[132],"they":[133],"achieve":[135],"promising":[136],"detection":[137],"performance":[138],"when":[139],"tested":[140],"disjoint":[142],"ASVspoof2015,":[143],"significantly":[144],"better":[145],"than":[146],"existing":[148],"cross-dataset":[149],"results.":[150],"This":[151],"reveals":[153],"great":[155],"potential":[156],"DNNs":[159],"without":[164],"features.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":52},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":35},{"year":2022,"cited_by_count":15}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2021-06-22T00:00:00"}