Xi Chen
School of Music, Shaanxi Normal University, Xi'an, Shaanxi 710119, China.
Comput Intell Neurosci. 2021 Sep 3;2021:6592938. doi: 10.1155/2021/6592938. eCollection 2021.
The current music teaching can effectively improve students' music emotional expression indirectly. How to use the PSO-BP neural network to realize the quantitative research of music emotional expression is the current development trend. Based on this, this paper studies the influence factors of music emotion expression based on PSO-BP neural network and big data analysis. Firstly, a music emotion expression analysis model based on PSO-BP neural network algorithm is proposed. The autocorrelation function is used to simulate the emotion expression information in music. Through the maximum value of the autocorrelation function curve in the detection process, the vocal music signal is restored, and then the emotion expressed is analyzed. Secondly, the influence factors of PSO-BP neural network algorithm in music emotion expression are analyzed. The improved PSO-BP neural network algorithm and multidimensional data model are used for comprehensive analysis to accurately analyze the emotion in music expression, and the fuzzy evaluation method and analytic hierarchy process are used for quality evaluation. Finally, the validity of the music emotion analysis model is verified by many experiments.
当前的音乐教学能够间接地有效提升学生的音乐情感表达能力。如何运用粒子群优化-反向传播（PSO-BP）神经网络来实现音乐情感表达的量化研究是当前的发展趋势。基于此，本文基于PSO-BP神经网络和大数据分析研究音乐情感表达的影响因素。首先，提出一种基于PSO-BP神经网络算法的音乐情感表达分析模型。利用自相关函数来模拟音乐中的情感表达信息。通过检测过程中自相关函数曲线的最大值来恢复声乐信号，进而分析所表达的情感。其次，分析PSO-BP神经网络算法在音乐情感表达中的影响因素。运用改进的PSO-BP神经网络算法和多维数据模型进行综合分析，以准确分析音乐表达中的情感，并采用模糊评价法和层次分析法进行质量评估。最后，通过多次实验验证了音乐情感分析模型的有效性。
