Transfer Learning of Artist Group Factors to Musical Genre Classification

Abstract

The automated recognition of music genres from audio information is a challenging problem, as genre labels are subjective and noisy. Artist labels are less subjective and less noisy, while certain artists may relate more strongly to certain genres. At the same time, at prediction time, it is not guaranteed that artist labels are available for a given audio segment. Therefore, in this work, we propose to apply the transfer learning framework, learning artist-related information which will be used at inference time for genre classification. We consider different types of artist-related information, expressed through artist group factors, which will allow for more efficient learning and stronger robustness to potential label noise. Furthermore, we investigate how to achieve the highest validation accuracy on the given FMA dataset, by experimenting with various kinds of transfer methods, including single-task transfer, multi-task transfer and finally multi-task learning.

Learning to Recognize Musical Genre from Audio

“…6 The plot only shows submissions with log loss < 5. ensemble methods outperformed neural networks, with XGBoost performing best. In [2], the authors argued that genres are subjective and noisy labels, whereas artists are more objective labels. As an artist is commonly part a subset of genres, and that sets of artists can be seen as exemplars for genres, they hypothesized that musical characteristics which identify an artist may also be key features of certain genres.…”

“…Docker containers were built out of those repositories. 2 We then ran them against a new unseen test set which was sampled from new contributions to the Free Music Archive.…”

Machine Translation in Low-Resource Languages by an Adversarial Neural Network

“…This block includes dense exponential linear units (ELU) [35] and a convolutional layer in sequence to fuse their embeddings thoroughly. An ELU activation function tends to converge errors to zero faster and produce more accurate results in real tasks than the rectified linear unit (RELU) [36]. For the Res Block, the residual connection converges faster under the premise of the same number of layers.…”