We describe feature space and model space discriminative training for a new class of acoustic models called Bayesian sensing hidden Markov models (BS-HMMs). In BS-HMMs, speech dat...
This paper combines a parameter generation algorithm and a model optimization approach with the model-integration-based voice conversion (MIVC). We have proposed probabilistic int...
Recent research in robot exploration and mapping has focused on sampling environmental hotspot fields. This exploration task is formalized by Low, Dolan, and Khosla (2008) in a se...
We propose dynamical systems trees (DSTs) as a flexible model for describing multiple processes that interact via a hierarchy of aggregating processes. DSTs extend nonlinear dynam...
Off-road autonomous navigation is one of the most difficult automation challenges from the point of view of constraints on mobility, speed of motion, lack of environmental structur...