A Novel Music Emotion Recognition Model Using Neural Network Technology.

Area of Science:

• Computer Science
• Artificial Intelligence
• Music Information Retrieval

Background:

• The rapid growth of music necessitates advanced organization, classification, and retrieval methods.
• Existing music emotion recognition (MER) methods struggle with dynamic emotional changes in music and capturing its deeper connotations.
• Personalized user needs increasingly focus on the emotional expression and psychological characteristics of music.

Purpose of the Study:

• To address the limitations of traditional MER techniques.
• To develop a more accurate and efficient system for recognizing emotions in music.
• To improve the global search capability and convergence speed of neural network models in MER.

Main Methods:

• An improved back propagation (BP) neural network architecture was employed for music data analysis.
• The artificial bee colony (ABC) algorithm was integrated to optimize the initial weights and thresholds of the BP network.
• The ABC algorithm was utilized to enhance the global search ability and reduce local optima in the BP network.

Main Results:

• The proposed MER method demonstrated superior recognition accuracy compared to other comparative models.
• The integrated ABC-BP model exhibited a faster recognition speed.
• Experimental results on public music datasets validated the effectiveness of the proposed approach.

Conclusions:

• The integration of the ABC algorithm significantly enhances the performance of BP neural networks for MER.
• The developed MER system offers improved accuracy and efficiency, meeting the growing demand for sophisticated music analysis.
• This approach provides a robust solution for understanding the emotional nuances within music.