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

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 classifiers with low computational cost and only minimal preprocessing. We obtain competitive classification scores and useful instrumentwise 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.

An Automatic Classification System for Environmental Sound in Smart Cities

“…With the continuous development of deep learning technology, the use of neural network technology for image and signal processing has become the choice of more and more researchers [ 5 , 6 ]. Especially in speech- and audio-related tasks [ 7 , 8 ], neural network techniques have performed better than traditional machine learning algorithms. Neural networks extract critical features from audio signals to classify ambient sounds efficiently and accurately [ 9 , 10 , 11 ].…”