最大似然（ML）准则和最大后验概率（MAP）准则，通过虚拟阵元进行DOA估计，数据模型归一化，模态振动，快速扩展随机生成树算法，实现了对10个数字音的识别，计算加权加速度。-Maximum Likelihood (ML) criteria and maximum a posteriori (MAP) criterion, Conducted through virtual array DOA estimation, Normalized data model, modal vibration, Rapid expansion of random spanning tree algorithm, To achieve the recognition of 10 digital sound, Weighted acceleration.