Music Segmentation Algorithm Based on Self-Adaptive Update of Confidence Measure

Jianhua Li,Naeem Jan

doi:10.1155/2021/8329088

Abstract

To improve the accuracy of music segmentation and enhance segmentation effect, an algorithm based on the adaptive update of confidence measure is proposed. According to the theory of compressed sensing, the music fragments are denoised, and thus the denoised signals are subjected to short-term correlation analysis. Then, the pitch frequency is extracted, and the music fragments are roughly classified by wavelet transform to realize the preprocessing of the music fragments. In order to calculate the confidence measure of the music segment, the SVM method is used, whereas the adaptive update of the confidence measure is studied using reliable data selection algorithm. The dynamic threshold notes are segmented according to the update result to realize music segmentation. Experimental results show that the recall and precision values of the algorithm reach 97.5% and 93.8%, respectively, the segmentation error rate is low, and it can achieve effective segmentation of music fragments, indicating that the algorithm is effective.

Highlights

At present, the commonly used music segmentation methods mainly include real-time audio segmentation method based on adaptive threshold adjustment, audio segmentation algorithm based on hierarchical entropy detection, audio segmentation algorithm based on credibility change trend, and audio segmentation algorithm based on fixed-length window hierarchical detection
Experimental results show that the algorithm is an effective audio segmentation method. e audio segmentation algorithm based on the change trend of credibility adopts the fixed length sliding window detection structure to reduce the cumulative error, calculates the credibility of each audio frame in the window, and detects the jump point according to the change trend of credibility, Journal of Mathematics so as to avoid the false detection caused by threshold selection and hard threshold decision
The above methods can realize music segmentation because the noise interference is not considered, the error rate of segmentation results is high, and the accuracy needs to be improved. erefore, this paper proposes a music segmentation algorithm based on an adaptive update of confidence measure

Summary

Music Preprocessing

The accuracy of segmentation is taken into consideration, where we use vocal and nonvocal attributes of music segments. M can be set within a certain range according to the actual situation of the music, so as to ensure that the music with emotional changes can stably stay in its emotional domain for a period of time, so that the emotional information of this music segment can be fully displayed. Otherwise, it needs to be regarded as an invalid emotional expression segment, so the whole music can be roughly classified according to the local intensity and rhythm of the music. In order to achieve accurate music segmentation, further research is conducted on the segmentation algorithm

Music Segment Processing Based on Adaptive Update of Confidence Measure

Simulation Experiment

Conclusion