Based on a recent development in the area of error control coding, we introduce the notion of convolutional factor graphs (CFGs) as a new class of probabilistic graphical models. ...
In this paper we introduce a novel way of modeling distributions with a low latent dimensionality. Our method allows for a strict control of the properties of the mapping between ...
Modern approaches to speaker recognition (verification) operate in a space of “supervectors” created via concatenation of the mean vectors of a Gaussian mixture model (GMM) a...
Balaji Vasan Srinivasan, Dmitry N. Zotkin, Ramani ...
We consider clustering situations in which the pairwise affinity between data points depends on a latent ”context” variable. For example, when clustering features arising fro...
In this paper, we offer broad insight into the underperformance of Arabic constituency parsing by analyzing the interplay of linguistic phenomena, annotation choices, and model de...