Sparse and Shift-invariant Feature Extraction from Non- negative Data

In Proc. of the IEEE International Conference on Audio and Speech Signal Processing (ICASSP)

Published December 18, 2008

Paris Smaragdis, B. Raj, M. Shashanka

In this paper we describe a technique that allows the extraction of multiple local shift-invariant features from analysis of non-negative data of arbitrary dimensionality. Our approach employs a probabilis- tic latent variable model with sparsity constraints. We demonstrate its utility by performing feature extraction in a variety of domains ranging from audio to images and video.

Learn More

Research Area:  AI & Machine Learning