An artificial neural network has been trained to recognize phonemes using the error back-propagation technique. First a coarse feature network is trained to extract seven quasi-phonetic features from the spectral frames of a Bark-scaled filter bank. The outputs of this net and the spectral outputs of the filter bank were input to a phoneme recognition net. The coarse features were recognized with 80% - 93% accuracy. Using manual segmentation the phone recognition rate was 64% and in 82% of the cases, the correct phone was among the best three candidates. Keywords: speech recognition; phoneme recognition; backword propagation; artificial neural networks