Sciweavers

933 search results - page 169 / 187
» A Fully Automatic hp-Adaptivity
Sort
View
CN
1998
95views more  CN 1998»
13 years 9 months ago
The Limits of Web Metadata, and Beyond
The World Wide Web currently has a huge amount of data, with practically no classification information, and this makes it extremely difficult to handle effectively. It has been re...
Massimo Marchiori
CORR
1998
Springer
113views Education» more  CORR 1998»
13 years 9 months ago
Letter to Sound Rules for Accented Lexicon Compression
This paper presents trainable methods for generating letter to sound rules from a given lexicon for use in pronouncing out-ofvocabulary words and as a method for lexicon compressi...
V. Pagel, Kevin Lenzo, Alan W. Black
CORR
1999
Springer
118views Education» more  CORR 1999»
13 years 9 months ago
Supervised Grammar Induction Using Training Data with Limited Constituent Information
Corpus-based grammar induction generally relies on hand-parsed training data to learn the structure of the language. Unfortunately, the cost of building large annotated corpora is...
Rebecca Hwa
JVCA
2002
157views more  JVCA 2002»
13 years 9 months ago
Realistic face animation for speech
We propose an efficient system for realistic speech animation. The system supports all steps of the animation pipeline, from the capture or design of 3D head models up to the synth...
Gregor A. Kalberer, Luc J. Van Gool
PAMI
2002
108views more  PAMI 2002»
13 years 9 months ago
Approximate Bayes Factors for Image Segmentation: The Pseudolikelihood Information Criterion (PLIC)
We propose a method for choosing the number of colors or true gray levels in an image; this allows fully automatic segmentation of images. Our underlying probability model is a hid...
Derek C. Stanford, Adrian E. Raftery