A time delay radial basis function network for phoneme recognition

This paper presents the time delay radial basis function network (TDRBF) for recognition of phonemes. The TDRBF combines features from time delay neural networks (TDNN) and radial basis functions (RBF). The ability to detect acoustic features and their temporal relationship independent of position in time is inherited from TDNN. The use of RBFs leads to shorter training times and less parameters to adjust, which makes it easier to apply TDRBF to new tasks. The recognition of three phonemes with about 750 training and testing tokens each was chosen as an evaluation task. The results suggest an equivalent performance of TDRBF and TDNN presented in Waibel et al. (1989), but TDRBF require much less training time to reach a good performance and in addition have a clear indication when the minimum error is reached, therefore no danger of overtraining exists.<
>