Deep Convolutional and Recurrent Networks for Polyphonic Instrument Classification from Monophonic Raw Audio Waveforms

TL;DR

This paper explores end-to-end deep learning models that classify musical instruments directly from raw audio waveforms, achieving competitive results with minimal preprocessing and low computational cost.

Contribution

It introduces a CNN-BiGRU model with residual connections for instrument classification from raw audio, reducing parameters while maintaining accuracy.

Findings

Competitive classification scores on IRMAS dataset

Effective instrument-wise insights from raw waveform input

Reduced model complexity with residual connections

Abstract

Sound Event Detection and Audio Classification tasks are traditionally addressed through time-frequency representations of audio signals such as spectrograms. However, the emergence of deep neural networks as efficient feature extractors has enabled the direct use of audio signals for classification purposes. In this paper, we attempt to recognize musical instruments in polyphonic audio by only feeding their raw waveforms into deep learning models. Various recurrent and convolutional architectures incorporating residual connections are examined and parameterized in order to build end-to-end classi-fiers with low computational cost and only minimal preprocessing. We obtain competitive classification scores and useful instrument-wise insight through the IRMAS test set, utilizing a parallel CNN-BiGRU model with multiple residual connections, while maintaining a significantly reduced number of trainable parameters.