A Deep Representation for Invariance And Music Classification

TitleA Deep Representation for Invariance And Music Classification
Publication TypeCBMM Memos
Year of Publication2014
AuthorsZhang, C, Evangelopoulos, G, Voinea, S, Rosasco, L, Poggio, T
Date Published03/2014
KeywordsAudio Representation, Hierarchy, Invariance, Machine Learning, Theories for Intelligence

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.





Download:  PDF icon CBMM-Memo-002.pdf
CBMM Memo No:  002

Research Area: 

CBMM Relationship: 

  • CBMM Funded