Abstract
Inspired by the success of deploying deep learning in the fields of Computer Vision and Natural Language Processing, this learning paradigm has also found its way into the field of Music Information Retrieval. In order to benefit from deep learning in an effective, but also efficient manner, deep transfer learning has become a common approach. In this approach, it is possible to reuse the output of a pre-trained neural network as the basis for a new learning task. The underlying hypothesis is that if the initial and new learning tasks show commonalities and are applied to the same type of input data (e.g., music audio), the generated deep representation of the data is also informative for the new task. Since, however, most of the networks used to generate deep representations are trained using a single initial learning source, their representation is unlikely to be informative for all possible future tasks. In this paper, we present the results of our investigation of what are the most important factors to generate deep representations for the data and learning tasks in the music domain. We conducted this investigation via an extensive empirical study that involves multiple learning sources, as well as multiple deep learning architectures with varying levels of information sharing between sources, in order to learn music representations. We then validate these representations considering multiple target datasets for evaluation. The results of our experiments yield several insights into how to approach the design of methods for learning widely deployable deep data representations in the music domain.
Highlights
In the Music Information Retrieval (MIR) field, many research problems of interest involve the automatic description of properties of musical signals, employing concepts that are understood by humans
While the representations resulting from the Multiple Single-Source Concatenated Representation (MSSCR) and various Multi-Source Concatenated Representations (MS-CR) architectures linearly depend on the chosen number of learning sources m, for MultiSource Shared Representation (MS-SR)@FC, which has a fixed dimensionality of d independent of m, we do notice increasing performance as more learning sources are used, except IRMAS dataset
We have investigated the effect of different strategies to learn music representations with deep networks, considering multiple learning sources and different network architectures with varying degrees of shared information
Summary
In the Music Information Retrieval (MIR) field, many research problems of interest involve the automatic description of properties of musical signals, employing concepts that are understood by humans. Tasks are derived that can be solved by automated systems. In such cases, algorithmic processes are employed to map raw music audio information to humanly understood descriptors (e.g., genre labels or descriptive tags). The task involves making a prediction based on a certain observation. Modern ML methodologies can be employed that automatically can infer the logic for the prediction directly from (a numeric representation of) the given data, by optimizing an objective function defined for the given task
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have