Traceback Translators Against Forgetting in Continual Fake Speech Detection
Enrico Gottardis, Mattia Tamiazzo, Simone Milani
cs.CV, cs.AI, cs.CR, cs.MM, cs.SD
Submitted: 2026-07-14
Comments: Accepted at EUSIPCO 2026
License: http://creativecommons.org/licenses/by/4.0/
The gist: Fake speech detectors are increasingly challenged by the development of new and more accurate generative models.
Terminology
Abstract
Fake speech detectors are increasingly challenged by the development of new and more accurate generative models. To cope with this problem, continual learning techniques are nowadays widely considered feasible strategies for updating models to new datasets, but they also lead to decreased performance on previously seen samples (catastrophic forgetting). In this work, we propose a forgetting-resilient solution based on the adoption of domain translators within a frozen detector, which remaps the new feature spaces into the original ones by means of a traceback translator network. Experimental results show that this strategy enables the achievement of high detection rates with respect to traditional retraining, while minimizing the computational effort and preserving the detection accuracy on previous data.
Sources
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models