Title: Tone detection for Indian classical polyphonic instrumental audio using DNN model

Authors: Ashwini; A. Vijaya Krishna; Vishal Mahesh; G.K. Karrthik

Addresses: Department of Electronics and Communication, PES University, Bengaluru – 560085, Karnataka, India ' Department of Electronics and Communication, PES University, Bengaluru – 560085, Karnataka, India ' Department of Electronics and Communication, PES University, Bengaluru – 560085, Karnataka, India ' Department of Electronics and Communication, PES University, Bengaluru – 560085, Karnataka, India

Abstract: Identification of tone from a polyphonic audio is quite a challenging task in digital audio processing. When the audio clip is a classical instrumental track the process is even more cumbersome. This paper proposes a novel approach to detect the tone of polyphonic Indian classical instrumental audio using scaled exponential linear unit (SeLu) activated Deep Neural Network (DNN) along with instrument identification which also uses SeLu activated DNN Model. This aims at utilising the same key features which help in instrument detection in real-life situations. The number of features were also reduced from 34 to 26 in comparison with the earlier work by analysing and identifying the redundant features and adding a few more important characteristic features. The proposed Instrument identification model predicts instruments with an accuracy of 84.39% for Carnatic classical and 83.59% for Hindustani classical. The SeLu activated DNN model for tone detection has attained an accuracy of 88.30%.

Keywords: instrument identification; tone detection; DNN; SeLu; scaled exponential linear unit; musical audio analysis; MIR.

DOI: 10.1504/IJFE.2020.115030

International Journal of Forensic Engineering, 2020 Vol.4 No.4, pp.310 - 322

Received: 17 Jul 2020
Accepted: 29 Sep 2020

Published online: 14 May 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article