Sciweavers

3371 search results - page 418 / 675
» Using parsimonious language models on web data
Sort
View
IJCAI
2003
15 years 8 months ago
Toward Conditional Models of Identity Uncertainty with Application to Proper Noun Coreference
Coreference analysis, also known as record linkage or identity uncertainty, is a difficult and important problem in natural language processing, databases, citation matching and ...
Andrew McCallum, Ben Wellner
GPCE
2007
Springer
16 years 20 days ago
A type-centric framework for specifying heterogeneous, large-scale, component-oriented, architectures
Maintaining integrity, consistency, and enforcing conformance in architectures of large-scale systems requires specification and enforcement of many different forms of structural...
Georg Jung, John Hatcliff
ICASSP
2008
IEEE
16 years 29 days ago
Optimizing the acoustic modeling from an unbalanced bi-lingual corpus
Phoneme set clustering of accurate modeling is important in the task of multilingual speech recognition, especially when each of the available language training corpora is mismatc...
Dau-cheng Lyu, Ren-yuan Lyu
DBPL
2003
Springer
92views Database» more  DBPL 2003»
15 years 11 months ago
A Query Algebra for Fragmented XML Stream Data
The increased usage of mobile devices coupled with an unprecedented demand for information has pushed the scalability problem of pull-based data service to the focus. A broadcast ...
Sujoe Bose, Leonidas Fegaras, David Levine, Vamsi ...
CIARP
2003
Springer
15 years 11 months ago
Creating a Mexican Spanish Version of the CMU Sphinx-III Speech Recognition System
Abstract. In this paper we present the creation of a Mexican Spanish version of the CMU Sphinx-III speech recognition system. We trained acoustic and N-gram language models with a ...
Armando Varela, Heriberto Cuayáhuitl, Juan ...