Abstract: Some scholars have applied the simultaneous perturbation stochastic approximation (SPSA) algorithm without secondary path modeling and with a relatively simple structure in active noise control research. To further enhance the algorithm's performance, this paper proposes introducing momentum into the iterative updating process of the control filter weight coefficients based on the existing SPSA algorithm, so that the noise reduction and convergence performance of the algorithm can be significantly improved by accumulating previous isotropic gradient information. The noise reduction effects of the proposed algorithm, the existing SPSA algorithm, and the filtered-x least mean square (FxLMS) algorithm are analyzed and compared through theoretical simulation and simulation using actual cabin noise signals. The results show that the proposed algorithm achieves better noise reduction performance than the existing SPSA algorithm, and its noise reduction effect is closer to that of the FxLMS algorithm. These results verify the effectiveness and superiority of the proposed algorithm.