Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Keras
Centre for Digital Music, Queen Mary University of London, London, UK
arXiv:1706.05781 [cs.SD], (19 Jun 2017)
@article{choi2017kapre,
title={Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Keras},
author={Choi, Keunwoo and Joo, Deokjin and Kim, Juho},
year={2017},
month={jun},
archivePrefix={"arXiv"},
primaryClass={cs.SD}
}
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.
June 21, 2017 by hgpu
