2025/02/03 by Yehuda Mishaly, Mishaly, Yehuda, Lior Wolf +3 · 2 citations
Computer Science · Engineering · #Speech and Audio Processing #Advanced Adaptive Filtering Techniques #Wireless Communication Networks Research
paper · pdf · doi:10.48550/arxiv.2502.01185
We present a novel deep learning network for Active Speech Cancellation (ASC), advancing beyond Active Noise Cancellation (ANC) methods by effectively canceling both noise and speech signals. The proposed Mamba-Masking architecture introduces a masking mechanism that directly interacts with the encoded reference signal, enabling adaptive and precisely aligned anti-signal generation-even under rapidly changing, high-frequency conditions, as commonly found in speech. Complementing this, a multi-band segmentation strategy further improves phase alignment across frequency bands. Additionally, we introduce an optimization-driven loss function that provides near-optimal supervisory signals for anti-signal generation. Experimental results demonstrate substantial performance gains, achieving up to 7.2dB improvement in ANC scenarios and 6.2dB in ASC, significantly outperforming existing methods.