Pattern recognition of speech signals is ability to translate a spoken word to text format. This paper presents an authority speech recognition system based on curvelet transform and artificial neural network techniques to enhance the recognition rate. This research comprised in two distinct phases, a feature extractor and recognizer is presented. In feature extraction phase, curvelet transform extract the features from the input speech signal and detail components of these signals which assist in achieving higher recognition rate. For feature matching, artificial neural networks is used as classifiers. The performance evaluation has been described in terms of accurate recognition rate, interfering sounds, hit rates, false alarm and miss rates. The rate of accurate classification was about 95.3 % for the sample speech signals.