Abstract
With the rapid growth of digital music today, due to the complexity of the music itself, the ambiguity of the definition of music category, and the limited understanding of the characteristics of human auditory perception, the research on topics related to automatic segmentation of music is still in its infancy, while automatic music is still in its infancy. Segmentation is a prerequisite for fast and effective retrieval of music resources, and its potential application needs are huge. Therefore, topics related to automatic music segmentation have important research value. This paper studies an improved algorithm based on negative entropy maximization for well-posed speech and music separation. Aiming at the problem that the separation performance of the negative entropy maximization method depends on the selection of the initial matrix, the Newton downhill method is used instead of the Newton iteration method as the optimization algorithm to find the optimal matrix. By changing the descending factor, the objective function shows a downward trend, and the dependence of the algorithm on the initial value is reduced. The simulation experimental results show that the algorithm can separate the source signal well under different initial values. The average iteration time of the improved algorithm is reduced by 26.2%, the number of iterations is reduced by 69.4%, and the iteration time and the number of iterations are both small. Fluctuations within the range better solve the problem of sensitivity to the initial value. Experiments have proved that the new objective function can significantly improve the separation performance of neural networks. Compared with the existing music separation methods, the method in this paper shows excellent performance in both accompaniment and singing in separated music.
Highlights
Music is the most common form of artistic expression in daily life, which greatly meets people’s spiritual and cultural needs and enriches people’s leisure life
Observing the experimental results of 30 sets of random initial matrices, the average iteration time of the improved algorithm is reduced by 26.2% and the number of iterations is reduced. e iteration time and the number of iterations fluctuate within a small range, which better solves the problem of sensitivity to the initial value
Maximizing negative entropy maximizes the non-Gaussian nature of random variables, thereby making the output components independent of each other. e negative entropy maximization algorithm takes negative entropy as the objective function and the Newton iteration method as the optimization algorithm
Summary
Music is the most common form of artistic expression in daily life, which greatly meets people’s spiritual and cultural needs and enriches people’s leisure life. E index structure established based on the results of the automatic segmentation will further improve the performance of the music retrieval system [6]. The segmenter can segment personal music collections according to emotions and scenes and can automatically select suitable records in different situations such as driving, meeting customers, and cleaning. Using the results of music segmentation, the automatic music transcription system can identify different styles of sound effects as corresponding notes [9]. E simulation experimental results show that the algorithm can separate the speech signal and music signal well under different initial values. The method in this paper has excellent performance in separating music. It is less affected by the separated signal and has strong universality and generalization performance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
