Research on Music Teaching and Creation Based on Deep Learning

Author:

Liu Mingxing1ORCID

Affiliation:

1. Shanxi Normal University, Linfen, Shanxi 041000, China

Abstract

Under the background of quality education, music learning is also changing, from the original shallow learning to deep learning gradually. In-depth learning is a new teaching concept, which pays full attention to students’ perception and exploration of music so that students can fully experience the charm of music. It can not only help students master more music knowledge and improve their music skills but also cultivate students’ music literacy and enhance their music ability (Świechowski, 2015). Therefore, in junior high school music teaching, teachers should actively apply the deep learning model and then improve the teaching level and comprehensively cultivate students’ music literacy (Whitenack and Swanson, 2003). In this paper, two convolution-based deep learning models, Breath1d and Breath2d, were designed and constructed, and a multilayer perceptron (MLP) was used as a benchmark method for performance evaluation, and a long short-term memory (LSTM) network is applied for the classification task. This paper discusses the value and application strategies of deep learning in junior high school music teaching and hopes to provide some reference for all educational colleagues (Zhang and Nauman 2020).

Funder

Shanxi Normal University

Publisher

Hindawi Limited

Subject

Computer Networks and Communications,Computer Science Applications

Reference15 articles.

1. A Constructivist View of Music Education: Perspectives for Deep Learning

2. Recent Advances in General Game Playing

3. Estimation of crowd density based on deep convolutional neural networks;Z. Tan;International Journal of Engineering Intelligent Systems for Electrical Engineering & Communications,2016

4. Checklist for responsible deep learning modeling of medical images based on COVID-19 detection studies

5. Deep Learning Based Syndrome Diagnosis of Chronic Gastritis

Cited by 9 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

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3