4451 search results - page 80 / 891 » Continuous model synthesis |
379
click to vote
Lab
VIMS Lab is situated in Department of Computer & Information Sc, University of Delaware, Newark, DE. USA.
At VIMS we work on various problems related to image/video processing...
154
click to vote
ICASSP
2009
IEEE
16 years 3 days ago
2009
IEEE
This paper introduces a new optimization technique for moving segment labels (phone and subphonetic) to optimize statistical parametric speech synthesis models. The choice of obje...
149
click to vote
IGPL
2006
15 years 5 months ago
2006
Since 1996, some models of recursive functions over the real numbers have been analyzed by several researchers. It could be expected that they exhibit a computational power much g...
184
click to vote
ICASSP
2011
IEEE
14 years 9 months ago
2011
IEEE
The context-independent deep belief network (DBN) hidden Markov model (HMM) hybrid architecture has recently achieved promising results for phone recognition. In this work, we pro...