We present a data-driven approach to learn user-adaptive referring expression generation (REG) policies for spoken dialogue systems. Referring expressions can be difficult to unde...
In the EMIME project we have studied unsupervised cross-lingual speaker adaptation. We have employed an HMM statistical framework for both speech recognition and synthesis which p...
Mikko Kurimo, William Byrne, John Dines, Philip N....
The goal of document image analysis is to produce interpretations that match those of a uent and knowledgeable human when viewing the same input. Because computer vision technique...
We propose a system that registers and retrieves text documents to annotate them on-line. The user registers a text document captured from a nearly top view and adds virtual annot...
Pictorial structure (PS) models are extensively used for part-based recognition of scenes, people, animals and multi-part objects. To achieve tractability, the structure and param...