{"id":"https://openalex.org/W4298397801","doi":"https://doi.org/10.1145/3552466.3556527","title":"Deep Spectro-temporal Artifacts for Detecting Synthesized Speech","display_name":"Deep Spectro-temporal Artifacts for Detecting Synthesized Speech","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4298397801","doi":"https://doi.org/10.1145/3552466.3556527"},"language":"en","primary_location":{"id":"doi:10.1145/3552466.3556527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3552466.3556527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.05254","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100375376","display_name":"Xiaohui Liu","orcid":"https://orcid.org/0000-0003-1589-1267"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaohui Liu","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457438","display_name":"Meng Liu","orcid":"https://orcid.org/0000-0002-1582-5764"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351795","display_name":"Lin Zhang","orcid":"https://orcid.org/0000-0001-7826-2850"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Lin Zhang","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","Taiyuan University of Technology, Taiyuan, China"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Taiyuan University of Technology, Taiyuan, China","institution_ids":["https://openalex.org/I9086337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075377676","display_name":"Linjuan Zhang","orcid":"https://orcid.org/0000-0003-4704-5807"},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]},{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Linjuan Zhang","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","Taiyuan University of Technology, Taiyuan, China"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Taiyuan University of Technology, Taiyuan, China","institution_ids":["https://openalex.org/I9086337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654128","display_name":"Chang Zeng","orcid":"https://orcid.org/0000-0002-4882-1823"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chang Zeng","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399953","display_name":"Kai Li","orcid":"https://orcid.org/0000-0002-9027-0914"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341055","display_name":"Nan Li","orcid":"https://orcid.org/0000-0002-3412-6408"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Li","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100375376"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.102,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3930903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.8469012379646301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6890112161636353},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6079436540603638},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5911620855331421},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5473839640617371},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4885474145412445},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47945916652679443},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.4442426562309265},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40944725275039673},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.30212342739105225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8469012379646301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6890112161636353},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6079436540603638},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5911620855331421},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5473839640617371},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4885474145412445},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47945916652679443},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.4442426562309265},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40944725275039673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30212342739105225},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3552466.3556527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3552466.3556527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.05254","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.05254","pdf_url":"https://arxiv.org/pdf/2210.05254","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:2210.05254","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.05254","pdf_url":"https://arxiv.org/pdf/2210.05254","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":0.5799999833106995,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7732325329","display_name":null,"funder_award_id":"62176182","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2079735306","https://openalex.org/W2103075368","https://openalex.org/W2123299109","https://openalex.org/W2157331557","https://openalex.org/W2176804518","https://openalex.org/W2187089797","https://openalex.org/W2745896134","https://openalex.org/W2792764867","https://openalex.org/W2887814324","https://openalex.org/W2928165649","https://openalex.org/W2954526560","https://openalex.org/W2972594541","https://openalex.org/W2972884023","https://openalex.org/W3036601975","https://openalex.org/W3037057938","https://openalex.org/W3089365019","https://openalex.org/W3094002217","https://openalex.org/W3094678546","https://openalex.org/W3095498208","https://openalex.org/W3128666957","https://openalex.org/W3131786367","https://openalex.org/W3140934869","https://openalex.org/W3143148229","https://openalex.org/W3154748208","https://openalex.org/W3157923770","https://openalex.org/W3163596559","https://openalex.org/W3181162804","https://openalex.org/W3183763412","https://openalex.org/W3196368020","https://openalex.org/W3196774886","https://openalex.org/W3197358873","https://openalex.org/W3197457172","https://openalex.org/W3197580070","https://openalex.org/W3198429080","https://openalex.org/W3198837656","https://openalex.org/W3199131409","https://openalex.org/W3199161700","https://openalex.org/W3199956586","https://openalex.org/W3200319900","https://openalex.org/W3200636257","https://openalex.org/W3201397251","https://openalex.org/W3209984917","https://openalex.org/W3212117663","https://openalex.org/W4221138880","https://openalex.org/W4224932929","https://openalex.org/W4225527248","https://openalex.org/W4226126880","https://openalex.org/W4287235833","https://openalex.org/W4300167667","https://openalex.org/W4309845474","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6743731764","https://openalex.org/W6753968785","https://openalex.org/W6761176859","https://openalex.org/W6784846362","https://openalex.org/W6801331058"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W2019977573","https://openalex.org/W2149980199","https://openalex.org/W2081900870","https://openalex.org/W3125766170"],"abstract_inverted_index":{"The":[0],"Audio":[1,30,37],"Deep":[2],"Synthesis":[3],"Detection":[4],"(ADD)":[5],"Challenge":[6],"has":[7],"been":[8],"held":[9],"to":[10,118],"detect":[11],"generated":[12],"human-like":[13],"speech.":[14],"With":[15],"our":[16,78,99],"submitted":[17],"system,":[18],"this":[19,40],"paper":[20],"provides":[21],"an":[22],"overall":[23],"assessment":[24],"of":[25,86,98,122],"track":[26,33,60,106,135,138],"1":[27,136],"(Low-quality":[28],"Fake":[29,36],"Detection)":[31],"and":[32,69,94,110,132,137],"2":[34],"(Partially":[35],"Detection).":[38],"In":[39],"paper,":[41],"spectro-temporal":[42],"artifacts":[43],"were":[44,75,112],"detected":[45,113],"using":[46,114],"raw":[47],"temporal":[48],"signals,":[49],"spectral":[50],"features,":[51],"as":[52,54],"well":[53],"deep":[55],"embedding":[56],"features.":[57],"To":[58],"address":[59],"1,":[61],"low-quality":[62],"data":[63],"augmentation,":[64],"domain":[65],"adaptation":[66],"via":[67],"finetuning,":[68],"various":[70],"complementary":[71],"feature":[72],"information":[73],"fusion":[74,102],"aggregated":[76],"in":[77,125,134],"system.":[79],"Furthermore,":[80],"we":[81],"analyzed":[82],"the":[83,96,120,126],"clustering":[84],"characteristics":[85],"subsystems":[87],"with":[88],"different":[89],"features":[90],"by":[91],"visualization":[92],"method":[93],"explained":[95],"effectiveness":[97],"proposed":[100],"greedy":[101],"strategy.":[103],"As":[104],"for":[105],"2,":[107,139],"frame":[108],"transition":[109],"smoothing":[111],"self-supervised":[115],"learning":[116],"structure":[117],"capture":[119],"manipulation":[121],"PF":[123],"attacks":[124],"time":[127],"domain.":[128],"We":[129],"ranked":[130],"4th":[131],"5th":[133],"respectively.":[140]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}