The main contribution is an interpretability-informed curriculum design for blind acoustic parameter estimation with clearer scope and improved reproducibility for ViT-based models.
This work frames this as Domain-Incremental Learning over acoustic environments and presents the first continual learning benchmark for multi-channel replay speech detection, evaluating a state-of-the-art beamformer-based detector over all 24 environment orderings of the ReMASC corpus with five seeds.
BLINC is proposed, a training-free TTA method that remaps the predicted time-frequency mask onto a bimodal target distribution by histogram matching and improves the overall quality of both evaluated SE models on almost every target condition and matches or exceeds the loss-based TTA baselines at minimal overhead.
Tobias Raichle, E. Gavrilko, Bin Yang· 0 citations
Increasing the overall realism of synthetic acoustic training data improves the generalization of DeepFilterNet3 to unseen measured environments and shows that increasing the overall realism of synthetic acoustic training data improves the generalization of DeepFilterNet3 to unseen measured environments.
Alessia Milo, G. Götz, S. Guðjónsson et al.· 2 citations
The transition from vocoder-based to neural-codec speech synthesis makes generalization more difficult for speech deepfake detectors, particularly those relying on speech-oriented representations. It remains unclear which acoustic representations retain discriminative information when the generation mechanism changes....
PRISM (Prototype-Rectified Iterative Self-supervised Manifold Denoising), a training-free, source-free TTA framework grounded in the Affine Noise Hypothesis, is addressed, making it substantially faster than gradient-based TTA while requiring no additional training.
A. Shukla, R. Thakur, Aryan Das et al.· 0 citations
Analysis of the results indicates that this multi-objective optimization framework achieves superior speech enhancement by simultaneously addressing magnitude and phase reconstruction, waveform-level distortion, and psychoacoustic naturalness, a balance not achieved in any prior works so far.
Debabrata Gogoi, Sushanta Kabir Dutta· Engineering Research Express· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.