Affiliation:
1. School of Teachers’ Training, Eastern Liaoning University, Dandong 118003, China
Abstract
It is one of the main goals of personalized music recommendation system that how to accurately recommend the songs in line with users’ interests in the huge music library. In view of the above problems, this study proposes a personalized music recommendation method based on convolutional neural network. First, this study defines a training set containing potential musical characteristics and, combined with the depth of the belief network, design a music information prediction model and the research in the music-type classification method with different dimensions. Based on selecting four different kinds of music information better describing the underlying characteristics of 40D feature vector to every song music composition, the music feature set is constructed. Then, the CNN (convolutional neural network), which is widely used in audio field, is used as the music information prediction model, and its structural parameters are redesigned to complete the multidimensional music information prediction, which solves the cold start problem to some extent.
Subject
General Engineering,General Mathematics
Reference36 articles.
1. Can digital consumption boost physical consumption? The effect of online music streaming on record sales
2. Music theme recognition using CNN and self-attention;M. Sukhavasi,2019
3. Cnn-based facial affect analysis on mobile devices;C. Hewitt,2018
4. 1D CNN architectures for music genre classification;S. Allamy
5. Learning to rank music tracks using triplet loss;L. Prétet
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献