{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T21:21:35Z","timestamp":1775856095436,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11230938","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Two Views, One Truth: Spectral and Self-Supervised Features Fusion for Robust Speech Deepfake Detection"],"prefix":"10.1109","author":[{"given":"Yassine","family":"El Kheir","sequence":"first","affiliation":[{"name":"DFKI,Speech and Language Technology,Germany"}]},{"given":"Arnab","family":"Das","sequence":"additional","affiliation":[{"name":"DFKI,Speech and Language Technology,Germany"}]},{"given":"Enes Erdem","family":"Erdogan","sequence":"additional","affiliation":[{"name":"DFKI,Speech and Language Technology,Germany"}]},{"given":"Fabian","family":"Ritter-Guttierez","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]},{"given":"Tim","family":"Polzehl","sequence":"additional","affiliation":[{"name":"DFKI,Speech and Language Technology,Germany"}]},{"given":"Sebastian","family":"M\u00f6ller","sequence":"additional","affiliation":[{"name":"DFKI,Speech and Language Technology,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2025.100757"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890588"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref4","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref5","article-title":"Deepfake audio is a political nightmare","author":"Meaker","year":"2023"},{"key":"ref6","article-title":"Beware the artificial impostor: A mcafee cybersecurity artificial intelligence report 2023","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-12"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-11"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10921"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-14"},{"key":"ref14","article-title":"Multi-perspective information fusion res2net with randomspecmix for fake speech detection","author":"Dong","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-702"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448095"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1383"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446331"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446560"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-247"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10796"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-260"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890563"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/s25071989"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.227"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.21437\/ASVspoof.2024-1","article-title":"Asvspoof 5: Crowdsourced speech data, deepfakes, and adversarial attacks at scale","author":"Wang","year":"2024"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017"},{"key":"ref32","article-title":"Generalizable speech deep-fake detection via meta-learned lora","author":"Laakkonen","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-403"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-481"},{"key":"ref37","first-page":"67 901","article-title":"Slim: Style-linguistics mismatch model for generalized audio deepfake detection","volume":"37","author":"Zhu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888990"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-659"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3626963"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746213"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"Tahoe City, CA, USA","start":{"date-parts":[[2025,10,12]]},"end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11230938.pdf?arnumber=11230938","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:58:25Z","timestamp":1763193505000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230938\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230938","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}