{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T18:46:29Z","timestamp":1781635589256,"version":"3.54.5"},"reference-count":72,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004725","name":"Ministry of Economic Affairs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650962","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-7","source":"Crossref","is-referenced-by-count":63,"title":["MLAAD: The Multi-Language Audio Anti-Spoofing Dataset"],"prefix":"10.1109","author":[{"given":"Nicolas M.","family":"M\u00fcller","sequence":"first","affiliation":[{"name":"Fraunhofer AISEC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piotr","family":"Kawa","sequence":"additional","affiliation":[{"name":"Wrocław University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei Herng","family":"Choong","sequence":"additional","affiliation":[{"name":"Fraunhofer AISEC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edresson","family":"Casanova","sequence":"additional","affiliation":[{"name":"Coqui.ai"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eren","family":"G\u00f6lge","sequence":"additional","affiliation":[{"name":"Coqui.ai"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thorsten","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Thorsten-Voice"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piotr","family":"Syga","sequence":"additional","affiliation":[{"name":"Wrocław University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip","family":"Sperl","sequence":"additional","affiliation":[{"name":"Fraunhofer AISEC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Konstantin","family":"B\u00f6ttinger","sequence":"additional","affiliation":[{"name":"Fraunhofer AISEC"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref2","article-title":"Apple introduces new features for cognitive accessibility, along with live speech, personal voice, and point and speak in magnifier","year":"2023"},{"key":"ref3","article-title":"Fraudsters cloned company director\u2019s voice in $35 million bank heist, police find","year":"2023"},{"key":"ref4","article-title":"Voice fraud scams company out of 243,000 dollars","year":"2023"},{"key":"ref5","article-title":"Ai-generated voice firm clamps down after 4chan makes celebrity voices for abuse","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref8","article-title":"Content authenticity initiative"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref11","article-title":"\"ai putin\" gave his chilling new year message, viewers convinced after \u2018telltale sign\u2019 spotted as death rumours swirl \u2014 the sun","author":"Sun"},{"key":"ref12","article-title":"Deepfake elections: How indian politicians are using ai-manipulated media to malign","author":"India"},{"key":"ref13","article-title":"Intelligence artificielle: quand un deepfake d\u2019emmanuel macron emballe la toile","author":"Croix"},{"key":"ref14","article-title":"The m-ailabs speech dataset","year":"2023"},{"key":"ref15","article-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Khalid"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906599"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094779"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233236"},{"key":"ref19","article-title":"WaveFake: A Data Set to Facilitate Audio Deepfake Detection","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Frank"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref21","article-title":"Add 2023: the second audio deepfake detection challenge","author":"Yi","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95398-0_9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-930"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2024.103122"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2867"},{"key":"ref27","article-title":"Better speech synthesis through scaling","author":"Betker","year":"2023"},{"key":"ref28","article-title":"Xtts: Open model release announcement"},{"key":"ref29","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref31","article-title":"Effective use of variational embedding capacity in expressive end-to-end speech synthesis","author":"Battenberg","year":"2019"},{"key":"ref32","article-title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","author":"Casanova","year":"2021"},{"key":"ref33","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1996"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-319"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref38","article-title":"Coqui TTS","author":"Eren","year":"2021"},{"key":"ref39","article-title":"SpeechBrain","author":"Ravanelli"},{"key":"ref40","first-page":"38","volume-title":"Transformers: State-of-the-Art Natural Language Processing","author":"Wolf","year":"2020"},{"key":"ref41","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref42","article-title":"The blizzard challenge 2013","author":"King","year":"2014"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1500"},{"key":"ref44","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref45","article-title":"Thorstenvoice dataset 2022.10","author":"M\u00fcller","year":"2022"},{"key":"ref46","article-title":"Github - dioco-group\/jenny-tts-dataset: A high-quality, varied \u02dc30hr voice dataset suitable for training a tts model"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-4"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-472"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-702"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom56396.2022.00111"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3437880.3460408"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747768"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1537"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-901"},{"key":"ref60","article-title":"Av-deepfake1m: A large-scale llm-driven audio-visual deepfake dataset","year":"2023"},{"key":"ref61","article-title":"nmt \u2022 pypi"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref63","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref64","article-title":"Sam: Accenture non-binary voice","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref67","first-page":"1015","article-title":"ESC: Dataset for Environmental Sound Classification","volume-title":"Proceedings of the 23rd Annual ACM Conference on Multimedia","author":"Piczak"},{"key":"ref68","article-title":"Free music archive - instrumental","author":"Archive","year":"2023"},{"key":"ref69","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"Snyder","year":"2015"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-9"},{"key":"ref71","article-title":"openai\/whisper-large \u2022 hugging face"},{"issue":"8","key":"ref72","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume-title":"Soviet physics doklady","volume":"10","author":"Levenshtein","year":"1966"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650962.pdf?arnumber=10650962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:21:22Z","timestamp":1725949282000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650962","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}