{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:22:55Z","timestamp":1780636975712,"version":"3.54.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746900","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"236-240","source":"Crossref","is-referenced-by-count":17,"title":["Adversarial Sample Detection for Speaker Verification by Neural Vocoders"],"prefix":"10.1109","author":[{"given":"Haibin","family":"Wu","sequence":"first","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Po-Chun","family":"Hsu","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Gao","sequence":"additional","affiliation":[{"name":"Tencent Research,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Research,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shen","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent Research,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Kang","sequence":"additional","affiliation":[{"name":"Tencent Research,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Centre for Perceptual and Interactive Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Towards robust neural vocoding for speech generation: A survey","author":"hsu","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017"},{"key":"ref10","article-title":"Defense for black-box at-tacks on anti-spoofing models by self-supervised learning","author":"wu","year":"2020","journal-title":"InterSpeech"},{"key":"ref11","first-page":"6564","author":"wu","year":"2020","journal-title":"ICASSP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101199"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2458"},{"key":"ref14","first-page":"6579","author":"li","year":"2020","journal-title":"ICASSP 2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2430"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3376897.3377856"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1955"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2983"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2441"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref4","first-page":"1962","author":"kreuk","year":"2018","journal-title":"ICASSP 2018"},{"key":"ref27","article-title":"Adversarial machine learning at scale","author":"kurakin","year":"2016"},{"key":"ref3","first-page":"5329","author":"snyder","year":"2018","journal-title":"ICASSP 2018"},{"key":"ref6","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref5","article-title":"The attacker’s perspective on automatic speaker verification: An overview","author":"das","year":"2020"},{"key":"ref8","first-page":"5231","article-title":"Imperceptible, robust, and targeted adversarial examples for automatic speech recognition","author":"qin","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref2","article-title":"A small footprint i-vector extractor","author":"kenny","year":"2012","journal-title":"Odyssey 2012-The Speaker and Language Recognition Workshop"},{"key":"ref9","first-page":"312","author":"liu","year":"2019","journal-title":"2019 IEEE ASRU"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","article-title":"Front-end factor analysis for speaker verification","volume":"19","author":"dehak","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1966"},{"key":"ref22","first-page":"202","article-title":"Improving the adversarial robustness for speaker verification by self-supervised learning","volume":"30","author":"wu","year":"2021","journal-title":"IEEE\/ACM TASLP"},{"key":"ref21","first-page":"6718","author":"wu","year":"2021","journal-title":"ICASSP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1452"},{"key":"ref23","article-title":"Adversarial attacks and defenses for speaker identification systems","author":"joshi","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746900.pdf?arnumber=9746900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:40Z","timestamp":1661199100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746900\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746900","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}