in Adv. in Neural Info. Proc. Systems, volume 9, MIT Press, 1997.

We seek to analyze and manipulate two factors, which we generically call style and content, underlying a set of observations. We t training data with bilinear models which explicitly represent the two-factor structure. These models can adapt easily during testing to new styles or content, allowing us to solve three general tasks: extrapolation of a new style to unobserved content; classi cation of content observed in a new style; and translation of new content observed in a new style. For classi cation, we embed bilinear models in a probabilistic framework, Separable Mixture Models (SMMs), which generalizes earlier work on factorial mixture models [7, 3]. Signi cant performance improvement on a benchmark speech dataset shows the bene ts of our approach.