The purpose of this paper is to introduce neural network-based methods that surpass state-of-the-art (SOTA) models, either by training faster or having simpler architecture, while maintaining comparable effectiveness in musical instrument identification in polyphonic music. Several approaches are presented, including two authors’ proposals, i.e., spiking neural networks (SNN) and a modular deep learning model named FMCNN (Fully Modular Convolutional Neural Network). First, a convolutional neural network (CNN) and convolutional-recurrent neural network (CRNN), adapted from literature, are built to detect up to 13 different instruments in polyphonic music. Furthermore, FMCNN and SNN are explored. The results obtained demonstrate that both FMCNN and SNN outperform traditional CNN and CRNN in terms of accurate instrument identification. Moreover, the SNN architecture is much less complex compared to other model sizes. These findings highlight the efficacy of the methods proposed in musical instrument identification in polyphonic audio.
Authors
- Maciej Blaszke,
- Grazina Korvel,
- prof. dr hab. inż. Bożena Kostek link open in new tab
Additional information
- DOI
- Digital Object Identifier link open in new tab 10.1109/mis.2024.3392586
- Category
- Publikacja w czasopiśmie
- Type
- artykuły w czasopismach dostępnych w wersji elektronicznej [także online]
- Language
- angielski
- Publication year
- 2024
