Automatic construction of neural networks for special purpose speech recognition systems

The successful application of speech recognition systems to new domains greatly depends on the tuning of the architecture to the new task, especially if the amount of training data is small. For example, the application of multi-layer perceptrons (MLPs) to speech recognition requires the optimization of the number of hidden units, the size of the input windows over time and the number of states that model an acoustic event. Previously, we have proposed the automatic structure optimization algorithm (ASO) that optimizes all of the above architectural parameters automatically. In this paper we (1) present results for the successful application of the ASO algorithm to connected spoken letter recognition, (2) show the suitability of the algorithm for various sizes of the system and (3) analyze the computational efficiency of the automatic optimization process for four different tasks