{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:27:43Z","timestamp":1775579263242,"version":"3.50.1"},"reference-count":26,"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\/icassp43922.2022.9747768","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"9241-9245","source":"Crossref","is-referenced-by-count":72,"title":["The Vicomtech Audio Deepfake Detection System Based on Wav2vec2 for the 2022 ADD Challenge"],"prefix":"10.1109","author":[{"given":"Juan M.","family":"Martin-Donas","sequence":"first","affiliation":[{"name":"Vicomtech Foundation, Basque Research and Technology Alliance (BRTA),Donostia – San Sebastián,Spain,20009"}]},{"given":"Aitor","family":"Alvarez","sequence":"additional","affiliation":[{"name":"Vicomtech Foundation, Basque Research and Technology Alliance (BRTA),Donostia – San Sebastián,Spain,20009"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref11","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"arXiv preprint arXiv 2006 11116"},{"key":"ref12","article-title":"Large-scale self-supervised speech representation learning for automatic speaker verification","author":"chen","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-847"},{"key":"ref15","article-title":"Investigating self-supervised front ends for speech spoofing countermeasures","author":"wang","year":"2021","journal-title":"arXiv preprint arXiv 2111 02269"},{"key":"ref16","article-title":"XLS-R: Self-supervised cross-lingual speech representation learning at scale","author":"babu","year":"2021","journal-title":"arXiv preprint arXiv 2111 02269"},{"key":"ref17","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"arXiv preprint arXiv 1607 08022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3076358"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-743"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2937413"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11235-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-738"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref20","article-title":"AISHELLl-3: A multi-speaker mandarin TTS corpus and the baselines","author":"shi","year":"2020","journal-title":"arXiv preprint arXiv 2010 11567"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-10"},{"key":"ref21","article-title":"English multi-speaker corpus for CSTR voice cloning toolkit","author":"yamagishi","year":"2012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-5"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref26","first-page":"89","article-title":"Pin-drop Labs’ Submission to the ASVspoof 2021 Challenge","author":"chen","year":"2021","journal-title":"Proc 2021 ASVspoof Workshop"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-12"}],"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\/09747768.pdf?arnumber=9747768","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:12:17Z","timestamp":1661184737000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747768\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747768","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}