Online Music Style Recognition via Mobile Computing

Online Music Style Recognition via Mobile Computing

Lizhu Yuan, Yue Zhang
DOI: 10.4018/IJMCMC.293748
Article PDF Download
Open access articles are freely available for download

Abstract

Music is a widely used data format in the explosion of Internet information. Automatically identifying the style of online music in the Internet is an important and hot topic in the field of music information retrieval and music production. Recently, automatic music style recognition has been used in many real life scenes. Due to the emerging of machine learning, it provides a good foundation for automatic music style recognition. This paper adopts machine learning technology to establish an automatic music style recognition system. First, the online music is process by waveform analysis to remove the noises. Second, the denoised music signals are represented as sample entropy features by using empirical model decomposition. Lastly, the extracted features are used to learn a relative margin support vector machine model to predict future music style. The experimental results demonstrate the effectiveness of the proposed framework.
Article Preview
Top

1. Introduction

With the rapid development of the Internet, people begin to have the opportunity to come into contacting with different music styles around the world and enjoy the pleasure brought by music (Kohut 2018). Although the music has some different expression ways in different countries or nations, the music has always been able to express people's thoughts, convey people's thinking (Stewart 2019). The music fully expresses its value in human life.

Up to now, there are countless kinds and quantities of musical instruments, such as guitar, piano, erhu, and cello (Zhao 2019). At the same time, the storage methods of music files are becoming diversification, including WAV files, MIDI files, MP3 files and WMA files (Fu 2021). Each file format has its own storage characteristics. WAV files are easy to generate and edit, but the compression ratio is not high. MIDI file has small size and storage space and is especially adapted for the needs of long time music. MP3 file is also a very common music format, which has high compression rate and poor sound quality.

The emergence of musical instruments and the diversification of music storage methods promote the formation of music genres (Ojanen 2020). The common music genres include jazz, classical, pop, hip-hop, rock and roll, etc. Recently, music information retrieval has become a new research topic, and a large number of researchers have studied this field (Murthy 2018). Because some users are only interested in one genre of music, music recognition and classification system can divide music into different genres. In this way, it is convenient for users to search and manage music in different periods of time, such as sports and rest. When the same song is sung by different people, the songs are different due to the different range, timbre and the performance of various musical instruments. Exactly extracting features of music leads to the low efficiency of music genre classification and recognition. With the deepening of a large number of research works, the music genre classification and generation will gradually develop in a better direction.

With the rapid development of music storage and computer technology, digital audio processing technology has been greatly improved (Gao 2019). Music processing software is also diversified, such as windows recorder, tools when buying a sound disc (Liang 2021). Speech recognition, text to speech conversion, speech compression coding and other technologies have gradually begun to use computer technology instead of manual completion (Lero 2019; Delić 2019). These methods are based on digital audio processing. In general, a piece of music is vectored. The features of the music are represented as a series of numbers to store and transmit. Different formats of music are finally represented in digital form, which makes the analysis of music become very simple and efficient by combining with the music processing software in the computer. At the same time, with the rapid development of computer technology, the accuracy of analyzing and processing music has been greatly improved, and the cost is reduced.

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024)
Volume 14: 1 Issue (2023)
Volume 13: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing