Considering that real communication signals corrupted by noise are generally nonstationary, and time-frequency distributions are especially suitable for the analysis of nonstationary signals, time-frequency distributions are introduced for the modulation classification of communication signals. The extracted time-frequency features have good classification information, and they are insensitive to signal to noise ratio (SNR) variation. According to good classification by the correct rate of a neural network classifier, a multilayer perceptron (MLP) classifier with better generalization, as well as, addition of time-frequency features set for classifying six different modulation types has been proposed. Computer simulations show that the MLP classifier outperforms the decision-theoretic classifier at low SNRs, and the classification experiments for real MPSK signals verify engineering significance of the MLP classifier. Considering that real communication signals corrupted by noise are generally nonstationary, and time-frequency distributions are particularly suitable for the analysis of nonstationary signals, time-frequency distributions are introduced for the modulation classification of communication signals. The extracted time-frequency features have good classification information, and they are insensitive to signal to noise ratio (SNR) variation. According to a good classification by the correct rate of a neural network classifier, a multilayer perceptron (MLP) classifier with better generalization, as well as, addition of time-frequency features simulations show that the MLP classifier outperforms the decision-theoretic classifier at low SNRs, and the classification experiments for real MPSK signals verify engineering significance of the MLP classifier.