A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging
This work addresses the problem of optimizing audio preprocessing for music tagging, which is incremental as it refines existing methods rather than introducing new paradigms.
The paper investigated the impact of various audio preprocessing methods on music tagging with deep neural networks, finding that only magnitude compression is necessary while other common techniques are redundant.
In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression.