Convolutional neural network and recommendation algorithm for the new model of college music education

•Music education requires repeated practice and experience of music skills.•The algorithm studied in this paper can supplement information sources for the music.•Neural network combined with a recommendation algorithm to design a music.•It is helpful for teachers to timely and dynamically grasp the...

Full description

Saved in:
Bibliographic Details
Published in:Entertainment computing Vol. 48; p. 100612
Main Author: Bai, Hua
Format: Journal Article
Language:English
Published: Elsevier B.V 01.01.2024
Subjects:
Algorithm
Convolutional neural network
Music education
Music teaching
New model
Music education
New model
Algorithm
Convolutional neural network
Music teaching
ISSN:1875-9521, 1875-953X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Music education requires repeated practice and experience of music skills.•The algorithm studied in this paper can supplement information sources for the music.•Neural network combined with a recommendation algorithm to design a music.•It is helpful for teachers to timely and dynamically grasp the types of music that students like. With the rapid development of the field of artificial intelligence, we expect that AI+ music can produce a new music education model to help efficient college students improve their personal music level. In this paper, we design a convolutional neural network music recommendation system, including a user modeling module, audio feature extraction module recommendation algorithm module, etc., which can model students' music preferences to generate Top recommendations for target users. It is helpful for teachers to timely and dynamically grasp the types of music that students like. Experiments show that the proposed method has certain feasibility and effectiveness. Compared with other traditional music recommendation algorithms, we can make full use of the powerful advantages of deep neural network automatic feature extraction and integrate the historical behavior information of users' interaction with music.
ISSN:1875-9521
1875-953X
DOI:10.1016/j.entcom.2023.100612