{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:59:26Z","timestamp":1775199566126,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100011038","name":"Office of the Director of National Intelligence","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011039","name":"Intelligence Advanced Research Projects Activity","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011039","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434594","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Rapidly Adapting to New Voice Spoofing: Few-Shot Detection of Synthesized Speech Under Distribution Shifts"],"prefix":"10.1109","author":[{"given":"Ashi","family":"Garg","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Human Language Technology Center of Excellence"}]},{"given":"Zexin","family":"Cai","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Human Language Technology Center of Excellence"}]},{"given":"Henry Li","family":"Xinyuan","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Human Language Technology Center of Excellence"}]},{"given":"Leibny Paola","family":"Garc\u00eda-Perera","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Human Language Technology Center of Excellence"}]},{"given":"Kevin Duh Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Human Language Technology Center of Excellence"}]},{"given":"Matthew","family":"Wiesner","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Human Language Technology Center of Excellence"}]},{"given":"Nicholas","family":"Andrews","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Human Language Technology Center of Excellence"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446863"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29740"},{"key":"ref4","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"},{"key":"ref5","first-page":"5210","article-title":"AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","volume-title":"International Conference on Machine Learning","volume":"97","author":"Qian"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2024.1339159"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941175"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.06.010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08025-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1656"},{"issue":"226","key":"ref12","first-page":"1","article-title":"Underspecification presents challenges for credibility in modern machine learning","volume":"23","author":"D\u2019Amour","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","article-title":"ShiftySpeech: A Large-Scale Synthetic Speech Dataset with Distribution Shifts","author":"Garg","year":"2025"},{"key":"ref14","article-title":"Matching Networks for One Shot Learning","volume":"29","author":"Vinyals","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"1126","article-title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","volume-title":"International Conference on Machine Learning","author":"Finn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref20","article-title":"Few-Shot Detection of Machine-Generated Text using Style Representations","volume-title":"The Twelfth International Conference on Learning Representations","author":"Soto"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15919-0_19"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref25","article-title":"A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection","author":"Ren","year":"2021","journal-title":"arXiv preprint arXiv:2106.09022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832350"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2093"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-465"},{"key":"ref32","article-title":"A Study of FewShot Audio Classification","author":"Wolters","year":"2020","journal-title":"arXiv preprint arXiv:2012.01573"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2568"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890060"},{"key":"ref35","article-title":"Synthetic Speech Detection Using Meta-Learning with Prototypical Loss","author":"Pal","year":"2022","journal-title":"arXiv preprint arXiv:2201.09470"},{"key":"ref36","first-page":"1126","article-title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2956589"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2684705"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-467"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434594.pdf?arnumber=11434594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:56:00Z","timestamp":1775192160000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434594\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434594","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}