Predicting normal sound absorption coefficients from multimodal acoustic fields using a channel-prior attention-guided deep residual network

Accurate characterization of material sound absorption is essential for acoustic engineering and material design. However, the traditional two-microphone impedance tube method is fundamentally constrained by the plane-wave assumption, resulting in significant performance degradation beyond the cutoff frequency. To overcome this limitation, this paper proposes a channel-prior attention-guided deep residual network (CPAM-DRN) for predicting the normal sound absorption coefficient (NSAC) directly from multimodal sound pressure fields. Unlike traditional modal decomposition or cancellation techniques, the proposed method explicitly exploits higher-order modal information as informative features for sound absorption characterization, enabling wide-band measurements without reducing tube diameter or increasing the number of microphones. The framework integrates physical acoustic propagation knowledge with data-driven learning to enhance prediction accuracy and robustness. A numerical impedance tube model is established to generate multimodal datasets for training, validation, and testing, enabling the network to learn the nonlinear mapping between pressure fields and NSAC. Simulation results demonstrate excellent predictive performance, achieving an R 2 of 0.9863 and an RMSE of 0.0024 under multimodal conditions, while the traditional method fails beyond the cutoff frequency. Experimental validation further shows that the predicted absorption coefficients in the 2300-6000 Hz range are highly consistent with measurements obtained using commercial B&K equipment, with an average deviation of less than 0.03. These results demonstrate the effectiveness and generalization capability of the proposed method for data-driven wide-band sound absorption characterization.