Transmitting Encrypted Data by Wavelet Transform and Neural Network

With development of information and communication technology, data transmission becomes more critical day by day. Higher security for transmitting data is especially required. Therefore; we designed a new method to transmit data on the phone line where there is no speech signal on it. Statistic investigations in one communication center in Iran show that there is about 57% non-speech signal on the phone line. Because a person on one side of the phone line speaks and then waits to hear the voice of the other person on the other side and, therefore; this non-speech signal has a good capacity for transmitting data. This project can be divided in four parts. The first part is the automatic classification of speech signal from non-speech using feature vectors derived from the wavelet analysis. The second part is the classification of speech and nonspeech signals using neural network. For recognizing this two cluster (speech signal and non-speech signal), we used NN. The third part is encrypting data and forth part is transmitting encrypted data on non-speech signal on the phone line.