Abstract
Automatic recognition of instrument types from an audio signal is a challenging and a promising research topic. It is challenging as there has been work performed in this domain and because of its applications in the music industry. Different broad categories of instruments like strings, woodwinds, etc., have already been identified. Very few works have been done for the sub-categorization of different categories of instruments. Mel Frequency Cepstral Coefficients (MFCC) is a frequently used acoustic feature. In this work, a hierarchical scheme is proposed to classify string instruments without using MFCC-based features. Chroma reflects the strength of notes in a Western 12-note scale. Chroma-based features are able to differentiate from the different broad categories of string instruments in the first level. The identity of an instrument can be traced through the sound envelope produced by a note which bears a certain pitch. Pitch-based features have been considered to further sub-classify string instruments in the second level. To classify, a neural network, k-NN, Naïve Bayes' and Support Vector Machine have been used.
Highlights
In India several kinds of string type instruments are being employed since ancient times
To develop applications related to music and instrument classification, audio indexing, audio retrieval a good quality audio classification is essential
In this work, string instruments have been sub-classified without using Mel Frequency Cepstral Coefficients (MFCC) which is a first-rate aural feature but excessively used
Summary
In India several kinds of string type instruments are being employed since ancient times. In this work, string instruments have been sub-classified without using Mel Frequency Cepstral Coefficients (MFCC) which is a first-rate aural feature but excessively used. Kumari et al (2010) have worked with musical instruments of North India for example: flute, dholak, sitar, mandar and bhapang They have used a combination of MFCC and spectral features to design their feature set. Wavelet and MFCC based hierarchical scheme were suggested by Ghosal et al (2011) to categorize instrumental devices in wide-ranging groups like String, Woodwind, Percussion and Keyboard. They have not explored further sub-classification of instruments. Spectral Centroid or SC, MFCC, signal energy and ZCR are used in their feature vector
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
