Tag
This paper proposes progressive error curriculum training (PECT) to improve phoneme-to-text reconstruction robustness in visual speech recognition by gradually adapting to realistic phoneme prediction errors, achieving reduced word error rates on LRS2 and LRS3 benchmarks.
This paper introduces a structured parameterization for noise models in ELTO-based Kalman filters, enabling dynamic adaptation to non-stationary processes and improving state estimation performance in noisy, time-varying environments.
This paper introduces Semi-Supervised Noise Adaptation (SSNA), a novel framework that uses synthetic noise domains (e.g., Gaussian distributions) as surrogate source domains to improve generalization in semi-supervised learning settings. The proposed Noise Adaptation Framework (NAF) establishes a generalization bound and demonstrates improved target domain performance.