Extraction and evaluation model for the basic characteristics of MIDI file music

The audio track of music melody includes a lot of useful information of music melody, which is the basic of music character recognition and also the premise work in the design of the performance plan of music foundation. Five eigenvectors : pitch, length, tone tempo and strength are extracted for the expression of music melody, by which, the basic music character recognition system can be set up. A emotion model is formed by using BP neural network.200 songs with different emotional characteristic songs will be used as the sample data for the training and validation of the neural network. The results of validation shows the effectiveness of the emotion model.