Finetuning a pre-trained WavLM model via a three-stage strategy achieves high detection accuracy for deepfake environmental sounds on two benchmark datasets, outperforming training from scratch.
Dcase-2016-challenge-task-3,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Environmental Sound Deepfake Detection Using Deep-Learning Framework
Finetuning a pre-trained WavLM model via a three-stage strategy achieves high detection accuracy for deepfake environmental sounds on two benchmark datasets, outperforming training from scratch.