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

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.

ICML 2017 machine learning for music discovery

References in corpus (2)

• Automatic tagging using deep convolutional neural networks
• Blocks and Fuel: Frameworks for deep learning

Cited by in corpus (8)

• Transfer learning for music classification and regression tasks
• A neural attention model for speech command recognition
• A Tutorial on Deep Learning for Music Information Retrieval
• Entangled Watermarks as a Defense against Model Extraction
• Voice2Series: Reprogramming Acoustic Models for Time Series Classification
• A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition
• Exploiting Synchronized Lyrics And Vocal Features For Music Emotion Detection
• nnAudio: An on-the-fly GPU Audio to Spectrogram Conversion Toolbox Using 1D Convolution Neural Networks