Abstract: |
Music emotion is influenced by many features such as melody line, bass line rhythm, tempo, acoustic characters velocity and intensity. To detect the emotion that a musical piece represents, it is very important to extract some proper features from music and build a model based on them. In this research, some new features, including two main parts, are extracted. And a new model, using the features, about music emotion automatic detection based on BP neural network is proposed. The test results prove good accuracy of this method. Finally, the result and the future work are discussed.
|