Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Keras

TL;DR

Kapre provides GPU-accelerated audio preprocessing layers for Keras, simplifying deep neural network workflows by integrating signal processing directly into model architecture, with minimal computational overhead.

Contribution

It introduces a novel set of Keras layers for on-GPU audio preprocessing, streamlining deep learning workflows in music research.

Findings

Real-time on-GPU preprocessing is feasible with reasonable computational cost.

Kapre simplifies audio preprocessing pipeline integration.

Benchmark results demonstrate efficiency of GPU-based audio processing.

Abstract

We introduce Kapre, Keras layers for audio and music signal preprocessing. Music research using deep neural networks requires a heavy and tedious preprocessing stage, for which audio processing parameters are often ignored in parameter optimisation. To solve this problem, Kapre implements time-frequency conversions, normalisation, and data augmentation as Keras layers. We report simple benchmark results, showing real-time on-GPU preprocessing adds a reasonable amount of computation.