Sciweavers

17450 search results - page 3154 / 3490
» Numerical Methods with Applications
Sort
View
INTERSPEECH
2010
15 years 1 months ago
Rhythm and formant features for automatic alcohol detection
Two speech feature sets, RMS rhythmicity and formant frequencies F1-F4, are analyzed for their ability to distinguish alcoholized from sober speech. We describe the statistical fr...
Florian Schiel, Christian Heinrich, Veronika Neume...
INTERSPEECH
2010
15 years 1 months ago
Modeling liaison in French by using decision trees
French is known to be a language with major pronunciation irregularities at word endings with consonants. Particularly, the well-known phonetic phenomenon called Liaison is one of...
Josafá de Jesus Aguiar Pontes, Sadaoki Furu...
JGO
2010
100views more  JGO 2010»
15 years 1 months ago
On convex relaxations of quadrilinear terms
The best known method to find exact or at least -approximate solutions to polynomial programming problems is the spatial Branch-and-Bound algorithm, which rests on computing lower...
Sonia Cafieri, Jon Lee, Leo Liberti
JMLR
2010
121views more  JMLR 2010»
15 years 1 months ago
Sparse Semi-supervised Learning Using Conjugate Functions
In this paper, we propose a general framework for sparse semi-supervised learning, which concerns using a small portion of unlabeled data and a few labeled data to represent targe...
Shiliang Sun, John Shawe-Taylor
JMLR
2010
129views more  JMLR 2010»
15 years 1 months ago
Expectation Truncation and the Benefits of Preselection In Training Generative Models
We show how a preselection of hidden variables can be used to efficiently train generative models with binary hidden variables. The approach is based on Expectation Maximization (...
Jörg Lücke, Julian Eggert
« Prev « First page 3154 / 3490 Last » Next »