Continuous speech input for ASR processing is usually presegmented into speech stretches by pauses. In this paper, we propose that smaller, prosodically defined units can be ident...
Yi-Fen Liu, Shu-Chuan Tseng, Jyh-Shing Roger Jang,...
The pervasive sensing technologies found in smart environments offer unprecedented opportunities for monitoring and assisting the individuals who live and work in these spaces. As ...
Seun Deleawe, Jim Kusznir, Brian Lamb, Diane J. Co...
A variational level set method is developed for the supervised classification problem. Nonlinear classifier decision boundaries are obtained by minimizing an energy functional tha...
After building a classifier with modern tools of machine learning we typically have a black box at hand that is able to predict well for unseen data. Thus, we get an answer to the...
David Baehrens, Timon Schroeter, Stefan Harmeling,...
Contrastive Divergence (CD) is a popular method for estimating the parameters of Markov Random Fields (MRFs) by rapidly approximating an intractable term in the gradient of the lo...