{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:20:54Z","timestamp":1763018454692,"version":"3.40.5"},"reference-count":43,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T00:00:00Z","timestamp":1642550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T00:00:00Z","timestamp":1642550400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972127"],"award-info":[{"award-number":["61972127"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Int J of Intelligent Sys"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1002\/int.22825","type":"journal-article","created":{"date-parts":[[2022,1,20]],"date-time":"2022-01-20T05:31:52Z","timestamp":1642656712000},"page":"3090-3116","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Can you trust what you hear: Effects of audio\u2010attacks on voice\u2010to\u2010face generation system"],"prefix":"10.1155","volume":"37","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-1163-7926","authenticated-orcid":false,"given":"Yanxiang","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China"},{"name":"Key Laboratory of Knowledge Engineering with Big Data Ministry of Education (Hefei University of Technology) Hefei Anhui China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-6996-4009","authenticated-orcid":false,"given":"Yupeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China"},{"name":"Key Laboratory of Knowledge Engineering with Big Data Ministry of Education (Hefei University of Technology) Hefei Anhui China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-3774-5113","authenticated-orcid":false,"given":"Pengcheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China"},{"name":"Key Laboratory of Knowledge Engineering with Big Data Ministry of Education (Hefei University of Technology) Hefei Anhui China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-9091-7100","authenticated-orcid":false,"given":"Jinlin","family":"Guo","sequence":"additional","affiliation":[{"name":"College of System Engineering National University of Defense Technology Changsha Hunan China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2022,1,19]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6157"},{"key":"e_1_2_8_4_1","first-page":"67","article-title":"VGGFace2: a dataset for recognising faces across pose and age","author":"Cao Q","year":"2018","journal-title":"IEEE Int. Conf. Autom. Face Gesture Recognit"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2756440"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPIN52536.2021.9566072"},{"key":"e_1_2_8_7_1","doi-asserted-by":"crossref","unstructured":"SaonG KurataG SercuT et al. English conversational telephone speech recognition by humans and machines.arXiv e-prints. 2017;arXiv:1703.02136.","DOI":"10.21437\/Interspeech.2017-405"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2765836"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107546"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-10810-6"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2207397"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2505311"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2185041"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911527"},{"key":"e_1_2_8_15_1","first-page":"2672","volume-title":"Adv. Neural Inf. Process. Syst","author":"Goodfellow IJ","year":"2014"},{"key":"e_1_2_8_16_1","first-page":"5266","volume-title":"Adv. Neural Inf. Process. Syst","author":"Wen Y","year":"2019"},{"key":"e_1_2_8_17_1","unstructured":"ChoiH\u2010S ParkC LeeK. From inference to generation: end\u2010to\u2010end fully self\u2010supervised generation of human face from speech.arXiv e\u2010prints.2020;arXiv:2004.05830."},{"key":"e_1_2_8_18_1","unstructured":"SzegedyC ZarembaW SutskeverI et al. Intriguing properties of neural networks. In:\u00a0arXiv e\u2010prints.2013;arXiv:1312.6199."},{"key":"e_1_2_8_19_1","first-page":"387","article-title":"Evasion attacks against machine learning at test time","author":"Biggio B","year":"2013","journal-title":"Mach. Learn. Knowl. Discovery Databases"},{"key":"e_1_2_8_20_1","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nherrL KohlsK ZeilerS HolzT KolossaD. Adversarial attacks against automatic speech recognition systems via psychoacoustic hiding.arXiv e\u2010prints.2018;arXiv:1808.05665.","DOI":"10.14722\/ndss.2019.23288"},{"key":"e_1_2_8_21_1","doi-asserted-by":"crossref","unstructured":"CarliniN WagnerDA. Audio adversarial examples: targeted attacks on speech\u2010to\u2010text.arXiv e\u2010prints.2018;arXiv:1801.01944v2.","DOI":"10.1109\/SPW.2018.00009"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSP51677.2021.9357499"},{"key":"e_1_2_8_23_1","unstructured":"QinY CarliniN GoodfellowIJ CottrellGW RaffelC. Imperceptible robust and targeted adversarial examples for automatic speech recognition.arXiv e\u2010prints.2019;arXiv:1903.10346v2."},{"key":"e_1_2_8_24_1","first-page":"712","article-title":"Hear \u201cNo Evil\u201d, see \u201cKenansville\u201d: efficient and transferable black\u2010box attacks on speech recognition and voice identification systems","author":"Abdullah H","year":"2019","journal-title":"2021 IEEE Symp. Secur. Priv."},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2187181"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-9739-8_3"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053076"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_2_8_29_1","unstructured":"GoodfellowIJ ShlensJ SzegedyC. Explaining and harnessing adversarial examples.arXiv e\u2010prints.2014;arXiv:1412.6572v3."},{"key":"e_1_2_8_30_1","unstructured":"MadryA MakelovA SchmidtL TsiprasD VladuA. Towards deep learning models resistant to adversarial attacks.arXiv e\u2010prints.2017;arXiv:1706.06083v4."},{"key":"e_1_2_8_31_1","unstructured":"MudaL BegamM ElamvazuthiI. Voice recognition algorithms using Mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques.arXiv e\u2010prints.2010;arXiv:1003.4083v1."},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6295-8"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5928"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"e_1_2_8_36_1","unstructured":"A Radford L Metz S Chintala 2015"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"e_1_2_8_38_1","unstructured":"D Snyder D Garcia\u2010Romero A McCree G Sell D Povey S Khudanpur Spoken language recognition using X\u2010vectors"},{"key":"e_1_2_8_39_1","article-title":"VoxCeleb: a large\u2010scale speaker identification dataset","author":"Nagrani A","year":"2017","journal-title":"arXiv e\u2010prints"},{"key":"e_1_2_8_40_1","article-title":"Speech commands: a dataset for limited\u2010vocabulary speech recognition","author":"Warden P","year":"2018","journal-title":"arXiv e\u2010prints"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"e_1_2_8_42_1","article-title":"Conformer: convolution\u2010augmented transformer for speech recognition","author":"Gulati A","year":"2020","journal-title":"arXiv e\u2010prints"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_2_8_44_1","article-title":"VoxCeleb2: deep speaker recognition","author":"Chung JS","year":"2018","journal-title":"arXiv e\u2010prints"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/int.22825","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/int.22825","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/int.22825","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T15:33:57Z","timestamp":1675956837000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/onlinelibrary.wiley.com\/doi\/10.1002\/int.22825"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,19]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["10.1002\/int.22825"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1002\/int.22825","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"type":"print","value":"0884-8173"},{"type":"electronic","value":"1098-111X"}],"subject":[],"published":{"date-parts":[[2022,1,19]]},"assertion":[{"value":"2021-07-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-03","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}