Music Score Recognition Method Based on Deep Learning

• Published in: Computational intelligence and neuroscience Vol. 2022; pp. 1 - 12
• Main Author: Lin, Qin
• Format: Journal Article
• Language: English
• Published: New York Hindawi 07.07.2022; John Wiley & Sons, Inc
• Subjects: Algorithms; Analysis; Artificial intelligence; Artificial neural networks; Belief networks; Classification; Data mining; Deep learning; Feature extraction; Information processing; Information retrieval; Knowledge representation; Machine learning; Methods; Music; Musical instruments; Musical scores; Neural networks; Propagation; Public domain; Sound tracks; Voice recognition
• ISSN: 1687-5265; 1687-5273; 1687-5273
• DOI: 10.1155/2022/3022767

In recent years, the recommendation application of artificial intelligence and deep music has gradually become a research hotspot. As a complex machine learning algorithm, deep learning can extract features with value laws through training samples. The rise of deep learning network will promote the development of artificial intelligence and also provide a new idea for music score recognition. In this paper, the improved deep learning algorithm is applied to the research of music score recognition. Based on the traditional neural network, the attention weight value improved convolutional neural network (CNN) and high execution efficiency deep belief network (DBN) are introduced to realize the feature extraction and intelligent recognition of music score. Taking the feature vector set extracted by CNN-DBN as input set, a feature learning algorithm based on CNN&DBN was established to extract music score. Experiments show that the proposed model in a variety of different types of polyphony music recognition showed more accurate recognition and good performance; the recognition rate of the improved algorithm applied to the soundtrack identification is as high as 98.4%, which is significantly better than those of other classic algorithms, proving that CNN&DBN can achieve better effect in music information retrieval. It provides data support for constructing knowledge graph in music field and indicates that deep learning has great research value in music retrieval field.