Musical Instrument Recognition in Polyphonic Audio Through Convolutional Neural Networks and Spectrograms
Loading...
Files
Size: 797.38 KB, File format: Adobe PDF
Date
Authors
Rujia, Chen
Ghobakhlou, Ali
Narayanan, Ajit
Supervisor
Item type
Degree name
Journal Title
Journal ISSN
Volume Title
Publisher
World Academy of Science, Engineering and Technology
Abstract
This study investigates the task of identifying musical instruments in polyphonic compositions using Convolutional Neural Networks (CNNs) from spectrogram inputs, focusing on binary classification. The model showed promising results, with an accuracy of 97% on solo instrument recognition. When applied to polyphonic combinations of 1 to 10 instruments, the overall accuracy was 64%, reflecting the increasing challenge with larger ensembles. These findings contribute to the field of Music Information Retrieval (MIR) by highlighting the potential and limitations of current approaches in handling complex musical arrangements. Future work aims to include a broader range of musical sounds, including electronic and synthetic sounds, to improve the model's robustness and applicability in real-time MIR systems.
Description
Keywords
binary classifier, CNN
Source
World Academy of Science, Engineering and Technology, International Journal of Electronics and Communication Engineering, Vol:18, No:07, 2024
DOI
Rights statement
© 2024 World Academy of Science, Engineering and Technology. Creative Commons Attribution 4.0 International License.
Permanent link
Endorsement
Review
Supplemented By
Referenced By
Creative Commons license
Except where otherwise noted, this item's license is described as © 2024 World Academy of Science, Engineering and Technology. Creative Commons Attribution 4.0 International License.