Deep learning has been successfully applied to perform non-linear embedding. In this paper, we present supervised embedding techniques that use a deep network to collapse classes....
Martin Renqiang Min, Laurens van der Maaten, Zinen...
State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptatio...
Many contemporary approaches to environmental sustainability focus on the end-consumer. In this panel, we explore lessons from small food producers for future development of HCI a...
Tad Hirsch, Phoebe Sengers, Eli Blevis, Richard Be...
I propose the concept of expressive surfaces as a research theme to investigate and explore aesthetics of computational objects with its emphasis on forms and materials. In this p...
We propose a new framework for speaker recognition, referred as Fishervoice. It includes the design of a feature representation known as the structured score vector (SSV), which r...