A Deep Representation for Invariance And Music Classification
This work addresses the problem of building invariant representations for audio signals, which could benefit music classification tasks, but appears incremental as it extends existing invariance theories to the audio domain.
The authors tackled the problem of learning invariant audio representations by proposing a mid-level representation based on empirical distributions of projections on transformed templates, which is theoretically guaranteed to be unique and invariant. They empirically evaluated this framework on music genre classification, though no concrete performance numbers are provided in the abstract.
Representations in the auditory cortex might be based on mechanisms similar to the visual ventral stream; modules for building invariance to transformations and multiple layers for compositionality and selectivity. In this paper we propose the use of such computational modules for extracting invariant and discriminative audio representations. Building on a theory of invariance in hierarchical architectures, we propose a novel, mid-level representation for acoustical signals, using the empirical distributions of projections on a set of templates and their transformations. Under the assumption that, by construction, this dictionary of templates is composed from similar classes, and samples the orbit of variance-inducing signal transformations (such as shift and scale), the resulting signature is theoretically guaranteed to be unique, invariant to transformations and stable to deformations. Modules of projection and pooling can then constitute layers of deep networks, for learning composite representations. We present the main theoretical and computational aspects of a framework for unsupervised learning of invariant audio representations, empirically evaluated on music genre classification.