A deep representation for invariance and music classification
Name
Poggio_A deep.pdf
Size
1.55 MB
Format
Adobe PDF
Checksum (MD5)
7ab9a6a3abf777a0eb463f2b53e1aae0
Author(s)
Zhang, Chiyuan
Evangelopoulos, Georgios
Voinea, Stephen Constantin
Rosasco, Lorenzo Andrea
Poggio, Tomaso A.
Date Issued
May 2014
Journal
Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Zhang, Chiyuan, Georgios Evangelopoulos, Stephen Voinea, Lorenzo Rosasco, and Tomaso Poggio. “A Deep Representation for Invariance and Music Classification.” 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (May 2014).
Version
Author's final manuscript
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.
MIT Department
Center for Brains, Minds, and Machines
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
McGovern Institute for Brain Research at MIT
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/ICASSP.2014.6854954
