How Low Can You Go? Reducing Frequency and Time Resolution in Current CNN Architectures for Music Auto-tagging
This work addresses efficiency trade-offs for researchers and practitioners in music information retrieval, though it is incremental as it builds on existing CNN architectures without introducing new methods.
The paper tackled the problem of reducing computational and storage costs in music auto-tagging by evaluating the impact of lowering frequency and time resolution in mel-spectrogram inputs for CNN models, finding that significant reductions can be made with minimal accuracy loss, such as achieving competitive performance with up to 75% fewer frequency bands.
Automatic tagging of music is an important research topic in Music Information Retrieval and audio analysis algorithms proposed for this task have achieved improvements with advances in deep learning. In particular, many state-of-the-art systems use Convolutional Neural Networks and operate on mel-spectrogram representations of the audio. In this paper, we compare commonly used mel-spectrogram representations and evaluate model performances that can be achieved by reducing the input size in terms of both lesser amount of frequency bands and larger frame rates. We use the MagnaTagaTune dataset for comprehensive performance comparisons and then compare selected configurations on the larger Million Song Dataset. The results of this study can serve researchers and practitioners in their trade-off decision between accuracy of the models, data storage size and training and inference times.