{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:24:58Z","timestamp":1775229898449,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"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":[[2025,4,24]]},"DOI":"10.1109\/iwbf63717.2025.11113428","type":"proceedings-article","created":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T18:11:50Z","timestamp":1755281510000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Emergent Capability in Audio Deepfake Detection"],"prefix":"10.1109","author":[{"given":"Yunbin","family":"Deng","sequence":"first","affiliation":[{"name":"MIT Lincoln Laboratory,Lexington,MA,USA"}]},{"given":"Alec","family":"Laprevotte","sequence":"additional","affiliation":[{"name":"California Institute of Technology,Pasadena,CA,USA"}]},{"given":"Robert","family":"Dunn","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory,Lexington,MA,USA"}]},{"given":"Pooya","family":"Khorrami","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory,Lexington,MA,USA"}]},{"given":"Charlie","family":"Dagli","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory,Lexington,MA,USA"}]},{"given":"Pedro","family":"Torres-Carrasquillo","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory,Lexington,MA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/a15050155"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3231480"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ojsp.2025.3529377"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-0827-1"},{"key":"ref7","volume-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020"},{"key":"ref8","author":"Tak","year":"2022","journal-title":"Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"issue":"97","key":"ref10","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref13","author":"Bird","year":"2023","journal-title":"Real-time Detection of AI-Generated Speech for DeepFake Voice Conversion"},{"key":"ref14","author":"Khalid","year":"2021","journal-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00097"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3276480"},{"key":"ref17","volume-title":"The Fake-or-Real Dataset"},{"key":"ref18","author":"Frank","year":"2021","journal-title":"Wavefake: A data set to facilitate audio deepfake detection"},{"key":"ref19","volume-title":"VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment","author":"Han","year":"2024"},{"key":"ref20","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref22","author":"Barrault","year":"2023","journal-title":"Seamless: Multilingual Expressive and Streaming Speech Translation"},{"key":"ref23","author":"Zhao","year":"2023","journal-title":"MeloTTS: High-quality Multi-lingual Multi-accent Text-to-Speech"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"},{"key":"ref25","volume-title":"The LJ Speech Dataset","author":"Ito","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref28","volume-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit, [sound]","author":"Veaux","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446331"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-021-06297-w"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446560"},{"key":"ref33","first-page":"67901","article-title":"Slim: Stylelinguistics mismatch model for generalized audio deepfake detection","volume":"37","author":"Zhu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.286"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3525966"},{"key":"ref36","author":"Yousif","year":"2024","journal-title":"Enhancing generalization in audio deepfake detection: A neural collapse based sampling and training approach"}],"event":{"name":"2025 13th International Workshop on Biometrics and Forensics (IWBF)","location":"Munich, Germany","start":{"date-parts":[[2025,4,24]]},"end":{"date-parts":[[2025,4,25]]}},"container-title":["2025 13th International Workshop on Biometrics and Forensics (IWBF)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11113384\/11113385\/11113428.pdf?arnumber=11113428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T06:01:04Z","timestamp":1755324064000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11113428\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iwbf63717.2025.11113428","relation":{},"subject":[],"published":{"date-parts":[[2025,4,24]]}}}