"The Modular approach and Neural Network (MNN) approach are well known concepts in the research and engineering community. By combining these two together, the Modular Neural Network (MNN) approach is very effective in searching for solutions to complex problems of various fields. This paper is the distribution of the complexity for the ambiguous words classification task on a set of modules. Each of these modules is a single neural network which is characterized by its high degree of specialization. The number of interfaces, and there with possibilities for filtering external acoustic - phonetic knowledge, increases a modular architecture."