Various Approaches in Musical Instrument Identification: A Review

Various Approaches in Musical Instrument Identification: A Review

Seema R. Chaudhary (MIT, Aurangabad, India) and Sangeeta N. Kakarwal (PESCOE, Aurangabad, India)
Copyright: © 2019 |Pages: 7
DOI: 10.4018/IJAEC.2019040101

Abstract

In the music information retrieval (MIR) field, it is highly desirable to know what instruments are used in an audio sample. Musical instrument classification is one of the sub domains of music information retrieval. Many researchers have presented different approaches for identifying western instruments and those approaches proved to be good for instrument identification. In this article, we have presented work done by the various authors to identify musical instrument using various approaches such sparse based representation, bio-inspired hierarchical model, joint modelling, Bayesian networks, neural networks, convolution neural networks, individual partials, clustering, and segmentation.
Article Preview
Top

1. Introduction

There is a huge demand for music search owing to the increasing number of music files in digital format. If an instrument information is included in the tags, it allows people to search for music with the specific instrument they want.

The prominent research done in Musical Information Retrieval includes singer identification, instrument identification, music transcription, query-based retrieval.

Musical instrument classification is one of the sub domain of music information retrieval. Many researchers invented different approaches for identifying western instruments and those approaches proved to be good for instrument identification.

It is being applied in music for automatic categorization, separating track and instrument identification, music transcription and recommender system.

1.1. Musical Sound

In general, a musical sound can be described with 4 perceptually oriented parameters – pitch, magnitude, duration and timbre. First three parameters are one dimensional in nature whereas musical timbre is multidimensional in nature and it also appears that it is the component of musical sound that is the most difficult to understand.

Resonators – Instruments tonal quality and loudness can change by hollowness or solidness in instrument. A resonator may be sound board of piano, harmonium or closed cavity in Indian instrument -tabla. Sound waves can cause other objects to move. For example – in string instruments like Sitar or Guitar, can cause another nearby string tuned to the same pitch to vibrate softly even though the second string was untouched. This phenomenon called sympathetic vibration. However, only the string tuned to the same note vibrates; the others are silent because they are not designed to move at that frequency. Each string has its own vibrating frequency, which depends on the string's length and tension. This frequency is called the resonant frequency of that string.

1.2. Types of Musical Instruments

Instruments are categorized by their musical function, their range, their method of producing a sound, their building material (wood, metal, stone, skin, etc.) and so on. Simple method of classification arranges instruments into three categories: string instruments (strings are the sounding body), wind instruments (blown through), and percussion instruments (struck). But more consistent way to arrange the instruments by precisely what makes the sound:

  • Chordophones (string instruments): A vibrating string, whether plucked, bowed, or struck, makes the sound;

  • Aerophones (wind instruments): A column of air within the instrument makes the sound;

  • Membranophones (drums): A membrane (skin) stretched over a resonator or frame makes the sound;

  • Idiophones: The entire instrument vibrates to make the sound;

  • Electrophones: The instrument makes sound through a loudspeaker.

1.3. Timbre

Timbre or tone color, is the psychoacoustic property of sound that allows the human brain to readily distinguish between two instances of the same note, each played on a different instrument.

Main problems underlying the complexity may be attributed to the following:

  • Timbre is a perceptual and subjective attribute of sound, rather than a purely physical one, making it a somewhat “non-tangible” entity;

  • Timbre is multidimensional in nature, where the qualities and importance of features, and the number of dimensions are not fully understood;

  • There are no current existing subjective scales to make judgments about timbre;

  • Timbre is an interdisciplinary research area that covers fields such as acoustics, music, computer science, engineering, and psychology;

  • There are no standard sets of sound examples against which the researcher can test their developed models.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2020): Forthcoming, Available for Pre-Order
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing