A New Adaptive Sound Zone Strategy-Based Hybrid FxNLMS and CNN-LSTM Network for Multichannel Active Noise Control in a Rehabilitation Room

Abstract

The equipment in the rehabilitation room can generate noise, affecting patients’ emotions and delaying their recovery. To create a quiet area in the rehabilitation room, a new adaptive sound zone strategy-based hybrid adaptive filter and deep learning network for a multichannel active noise control (ANC) system is proposed. First, to enhance the attenuation level in critical areas and achieve better robustness, a novel sound zone control strategy is integrated into the cost function of the proposed multichannel ANC (mcANC) algorithm. Then, an improved hybrid filtered-x normalized least mean square (FxNLMS) and convolutional neural network-based long short-term memory (CNN-LSTM) is utilized instead of a single-adaptive filter to reduce time-varying and long-term periodic noise. In addition, a new phase-tracking filter is employed to assist the CNN-LSTM in enhancing its phase-tracking ability. Moreover, the proposed hybrid FxNLMS and CNN-LSTM multichannel network is more effective at attenuating time-varying noise than the conventional single-filter network. Meanwhile, it offers superior noise reduction and real-time tracking performance compared to the deep ANC network. Also, compared with the conventional delay compensation method, the proposed phase tracking (PT) filter demonstrates a smaller statistical average phase error. Furthermore, simulations using recorded noise in a rehabilitation room model illustrate the efficiency of the proposed method.