Most HMM-based TTS systems use a hard voiced/unvoiced classification to produce a discontinuous F0 signal which is used for the generation of the source-excitation. When a mixed ...
Javier Latorre, Mark J. F. Gales, Sabine Buchholz,...
Dataflow formalisms have provided designers of digital signal processing systems with optimizations and guarantees to arrive at quality prototypes quickly. As system complexity in...
William Plishker, Nimish Sane, Mary Kiemb, Kapil A...
In this paper, a system for automatic robust video surveillance is described and in particular its application to the problem of locating vehicles that stop in prohibited area is ...
Simone Boragno, Boghos A. Boghossian, James Black,...
Monaural speech segregation in reverberant environments is a very difficult problem. We develop a supervised learning approach by proposing an objective function that directly rel...
One of the primary advantages of artificial neural networks is their inherent ability to perform massively parallel, nonlinear signal processing. However, the asynchronous dynamics...