ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Deep Single Shot Musical Instrument Identification using Scalograms

Chatterjee, D and Dutta, A and Sil, D and Chandra, A (2023) Deep Single Shot Musical Instrument Identification using Scalograms. In: 5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023, 20 - 23 February 2023, Virtual, Online, pp. 386-389.

[img]
Preview
PDF
icaiic_2023.pdf - Published Version

Download (695kB) | Preview
Official URL: https://doi.org/10.1109/ICAIIC57133.2023.10066992

Abstract

Musical instrument identification has for long had a reputation of being one of the most ill-posed problems in the field of musical information retrieval. Despite several robust attempts made at solving the problem, a timeline spanning over the last five odd decades, the problem remains an open conundrum. In this work, we take on a further complex version of the traditional problem, we attempt to solve the problem with minimal data available - one audio excerpt per class. We propose to use a convolutional Siamese network and a residual variant of the same to identify musical instruments based on the corresponding scalograms of their audio excerpts. Results obtained for two publicly available datasets validate our algorithm, achieving over 80% accuracy with only 5 sets of training data. Moreover, our proposed architectures work for both spectrograms as well as scalograms, and exhibit improvements, albeit marginal (≃ 3%), for the later input class.

Item Type: Conference Paper
Publication: 5th International Conference on Artificial Intelligence in Information and Communication, ICAIIC 2023
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: The copyright for this article belongs to the Authors.
Keywords: Audio acoustics; Convolution; Convolutional neural networks; Deep learning; Musical instruments, Audio excerpt; Convolutional siamese network; Ill posed problem; Musical information retrieval; Musical instrument identification; One-shot learning; Proposed architectures; Scalogram; Single-shot; Training data, Music
Department/Centre: Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited: 25 May 2023 03:29
Last Modified: 25 May 2023 03:29
URI: https://eprints.iisc.ac.in/id/eprint/81514

Actions (login required)

View Item View Item