MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation
Researchers have introduced MeCo, a novel one-step generative corrector for multi-channel speech separation. This method uses a MeanFlow-based approach to map estimated audio directly to clean speech, aiming to improve human listening quality beyond traditional discriminative models. MeCo incorporates Data-Space Optimization with an $\mathbf{x}_r$-loss and an Endpoint SI-SDR loss to enhance both signal fidelity and subjective listening experience. AI
IMPACT Improves audio processing quality and efficiency for speech separation tasks.