The invention provides a memory with a speech recognition function. The memory comprises a plurality of memory processing units, each unit comprising a mode processing circuit and at least one three-dimensional memory (3D-M) array. The 3D-M array is stacked on top of the mode processing circuit and stores user voice data and the like. The mode processing circuit according to an input acoustic model (or language model) to perform mode recognition on the user voice data stored in the 3D-M array.