Speech recognition experiments with a new multilayer LVQ network (MLVQ)

In this paper, a new neural network paradigm and its application to recognition of speech patterns is presented. The novel NN paradigm is a multilayer version of the well-known LVQ algorithm from Kohonen. The approach includes the following innovations and improvements compared to other popular neural network paradigms: 1) It is according to the knowledge of the author the first multilayer version of the classical LVQ algorithm, which is usually based on a one-layer neural network architecture. 2) It presents a new NN architecture, since it uses a perceptron-like propagation function for the hidden layers, and an Euclidean-like propagation function for the output layer. 3) Its architecture can be considered as an optimal compromise between the multilayer principle of an MLP and the principle of representing one class by several neurons adopted from classical LVQ. 4) Compared to MLP, the training of an MLVQ network with the same number of neurons is more effective, since only the weights of the winning neuron are updated, as in classical LVQ. 5) It outperforms both, the classical LVQ and the MLP algorithm in most experiments carried out. 6) In the initialization phase, the layers are trained hierarchically, making use of unsupervised information theory-based training algorithms.