论文部分内容阅读
In order to solve the problem of separation between singing and accompaniment in the musical signals,a music separation method based on repeating structural model and sound source separation is proposed. Firstly,the harmonic source and the percussive source of the music are separated by iterative method. Then the beat spectrum was introduced to analyze the energy spectrum matrix of the different sound sources. And the repeated periodic components of the harmonic source are retained to obtain accompaniment while the repeated periodic components of the percussive source are removed to separate the singing voice. On the MIR-1K dataset,the separation experimental results of 1000 music fragments show that the proposed method has an advantage over other existing music separation methods.