{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T09:50:46Z","timestamp":1726048246582},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T00:00:00Z","timestamp":1670803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T00:00:00Z","timestamp":1670803200000},"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":[[2022,12,12]]},"DOI":"10.1109\/wifs55849.2022.9975433","type":"proceedings-article","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T13:47:13Z","timestamp":1671025633000},"page":"1-6","source":"Crossref","is-referenced-by-count":11,"title":["Open Challenges in Synthetic Speech Detection"],"prefix":"10.1109","author":[{"given":"Luca","family":"Cuccovillo","sequence":"first","affiliation":[{"name":"Fraunhofer Institute for Digital Media Technology,Ilmenau,Germany"}]},{"given":"Christoforos","family":"Papastergiopoulos","sequence":"additional","affiliation":[{"name":"Centre for Research and Technology Hellas,Thessaloniki,Greece"}]},{"given":"Anastasios","family":"Vafeiadis","sequence":"additional","affiliation":[{"name":"Centre for Research and Technology Hellas,Thessaloniki,Greece"}]},{"given":"Artem","family":"Yaroshchuk","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Digital Media Technology,Ilmenau,Germany"}]},{"given":"Patrick","family":"Aichroth","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Digital Media Technology,Ilmenau,Germany"}]},{"given":"Konstantinos","family":"Votis","sequence":"additional","affiliation":[{"name":"Centre for Research and Technology Hellas,Thessaloniki,Greece"}]},{"given":"Dimitrios","family":"Tzovaras","sequence":"additional","affiliation":[{"name":"Centre for Research and Technology Hellas,Thessaloniki,Greece"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2923806"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1872"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"article-title":"TIMIT acoustic-phonetic continuous speech corpus","year":"1993","author":"garofolo","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3437880.3460408"},{"key":"ref30","first-page":"7586","article-title":"Non-autoregressive neural text-to-speech","author":"peng","year":"2020","journal-title":"Int Conference on Machine Learning"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6044"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682743"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref10","first-page":"104","article-title":"Detecting AI-synthesized speech using bispectral analysis","author":"albadawy","year":"2019","journal-title":"IEEE Conf Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3512732.3533585"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747186"},{"key":"ref13","article-title":"Wavefake: A data set to facilitate audio deepfake detection","author":"frank","year":"2021","journal-title":"International Conference on Neural Information Processing Systems (NeurIPS) – Datasets and Benchmark Track"},{"article-title":"ASVspoof 2021 challenge – speech deepfake database, version 1.0","year":"2021","author":"delgado","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-930"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906599"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","year":"2019","author":"yamagishi","key":"ref18"},{"key":"ref19","first-page":"223","article-title":"The CMU arctic speech databases","author":"kominek","year":"2004","journal-title":"ISCA Speech Synthesis Workshop"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413716"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2279"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2013.6712706"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2505"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-438"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-021-00116-3"},{"key":"ref1","first-page":"17 022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"International Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"year":"2006","key":"ref20","article-title":"VoxForge"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v38i3.2741"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"article-title":"The LJ Speech dataset","year":"2017","author":"ito","key":"ref21"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00077"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639511"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-19"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413397"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953080"},{"article-title":"Federated learning with non-IID data","year":"2018","author":"zhao","key":"ref43"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3133134"}],"event":{"name":"2022 IEEE International Workshop on Information Forensics and Security (WIFS)","start":{"date-parts":[[2022,12,12]]},"location":"Shanghai, China","end":{"date-parts":[[2022,12,16]]}},"container-title":["2022 IEEE International Workshop on Information Forensics and Security (WIFS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9975350\/9975299\/09975433.pdf?arnumber=9975433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T15:10:39Z","timestamp":1674486639000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9975433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,12]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/wifs55849.2022.9975433","relation":{},"subject":[],"published":{"date-parts":[[2022,12,12]]}}}