A Deep Bag-of-Features Model for Music Auto-Tagging
This work addresses music information retrieval for auto-tagging, presenting an incremental improvement in feature learning for this domain-specific task.
The paper tackles music auto-tagging by proposing a two-stage deep learning model that first learns sparse representations from audio and then fine-tunes a deep neural network, achieving high performance on the Magnatagatune dataset.
Feature learning and deep learning have drawn great attention in recent years as a way of transforming input data into more effective representations using learning algorithms. Such interest has grown in the area of music information retrieval (MIR) as well, particularly in music audio classification tasks such as auto-tagging. In this paper, we present a two-stage learning model to effectively predict multiple labels from music audio. The first stage learns to project local spectral patterns of an audio track onto a high-dimensional sparse space in an unsupervised manner and summarizes the audio track as a bag-of-features. The second stage successively performs the unsupervised learning on the bag-of-features in a layer-by-layer manner to initialize a deep neural network and finally fine-tunes it with the tag labels. Through the experiment, we rigorously examine training choices and tuning parameters, and show that the model achieves high performance on Magnatagatune, a popularly used dataset in music auto-tagging.