Learning data representations is a fundamental challenge in modeling neural processes and plays an important role in applications such as object recognition. In multi-stage Optima...
The basic finite automata model has been extended over the years with different acceptance modes (nondeterminism, alternation), new or improved devices (two-way heads, pebbles, ...
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....
■ Two experiments investigated the processes underlying the picture superiority effect on recognition memory. Studied pictures were associated with higher accuracy than studied ...
More and more fonts have sprung up in recent years in digital publishing industry and reading devices. In this paper, we focus on methods of evaluating digital Chinese fonts and t...