Music Instrument Identification Based on a 2-D Representation
Document Type
Conference Article
Publication Title
Third International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques, ICEECCOT 2018
Abstract
Automatic recognition of musical instruments has been a great problem in the field of digital signal processing. In this work a novel, compact set of features obtained by transforming a music signal to the spatial domain is introduced with promising results. Preliminary results on a popular music database, presented in terms of precision, recall and identification accuracy, are highly encouraging. The best result comprises an accuracy of 84.02% by Decision Tree (DT) for a set of 9 instruments belonging to different families. The accuracy for predicting the instrument family 96.07% for string family and for wind instrument the overall prediction accuracy is 90.78%. Further inclusion of some other features from some available works are also checked leading to slight increase in the accuracy. The obtained results are also compared with the result predicted by the VGG-16 network on the same dataset. The feature set containing 8 features that introduces less computational complexity compared to available works, may be considered as a major contribution. The comparison shows, we can replicate nearly accurate classification through our proposed method in less amount of time than deep neural architecture.
First Page
509
Last Page
513
DOI
10.1109/ICEECCOT43722.2018.9001486
Publication Date
12-1-2018
Recommended Citation
Ghosh, Alekhya; Pal, Arghadeep; Sil, Dibakar; and Palit, Sarbani, "Music Instrument Identification Based on a 2-D Representation" (2018). Conference Articles. 32.
https://digitalcommons.isical.ac.in/conf-articles/32