Low-Complexity Neural Wind Noise Reduction for Audio Recordings

Wind noise significantly degrades the quality of outdoor audio recordings, yet remains difficult to suppress in real time on resource-constrained devices. In this work, we propose a low-complexity, causal, single-channel deep neural network that leverages the spectral characteristics of wind noise through a dual encoder with a stronger low-frequency focus. Experimental results show that our method achieves performance comparable to the state-of-the-art, low-complexity ULCNet model. Furthermore, with only 249k parameters and roughly 0.05 % of the computational power of a single-core ARM Cortex-A53 processor, the proposed model is suitable for embedded audio applications.