In recent years, the computational effort for novel speech recognition systems has increased much more than the resulting recognition rates. Therefore, we present an approach for overcoming this drawback by using a modular phoneme recognition system. It combines advantages of neural networks with those of modular architectures. Important system features are module-specific selection of input parameters according to the decision tasks and the utilization of time delay neural networks (TDNNs) as well as static neural networks without time processing. The intention is to improve the recognition rate for speaker-independent phoneme recognition and, at the same time, to reduce the necessary effort for simulating the system after the initial learning phase.