Search
Now showing items 1-2 of 2
Nonlinear Latent Variable Models for Video Sequences
(2005-06-06)
Many high-dimensional time-varying signals can be modeled as a sequence of noisy nonlinear observations of a low-dimensional dynamical process. Given high-dimensional observations and a distribution describing the ...
The Unsupervised Acquisition of a Lexicon from Continuous Speech
(1996-01-18)
We present an unsupervised learning algorithm that acquires a natural-language lexicon from raw speech. The algorithm is based on the optimal encoding of symbol sequences in an MDL framework, and uses a hierarchical ...