Sciweavers

1291 search results - page 91 / 259
» Learning a language model from continuous speech
Sort
View
ENTCS
2010
133views more  ENTCS 2010»
14 years 10 months ago
Towards Measurable Types for Dynamical Process Modeling Languages
Process modeling languages such as "Dynamical Grammars" are highly expressive in the processes they model using stochastic and deterministic dynamical systems, and can b...
Eric Mjolsness
ICML
1999
IEEE
15 years 10 months ago
Monte Carlo Hidden Markov Models: Learning Non-Parametric Models of Partially Observable Stochastic Processes
We present a learning algorithm for non-parametric hidden Markov models with continuous state and observation spaces. All necessary probability densities are approximated using sa...
Sebastian Thrun, John Langford, Dieter Fox
ICASSP
2009
IEEE
14 years 7 months ago
Spoken language interpretation: On the use of dynamic Bayesian networks for semantic composition
In the context of spoken language interpretation, this paper introduces a stochastic approach to infer and compose semantic structures. Semantic frame structures are directly deri...
Marie-Jean Meurs, Fabrice Lefevre, Renato de Mori
NLPRS
2001
Springer
15 years 2 months ago
Topic Segmentation : A First Stage to Dialog-Based Information Extraction
We study the problem of topic segmentation of manually transcribed speech in order to facilitate information extraction from dialogs. Our approach is based on a combination of mul...
Narjès Boufaden, Guy Lapalme, Yoshua Bengio
ICASSP
2007
IEEE
15 years 4 months ago
Eigentongue Feature Extraction for an Ultrasound-Based Silent Speech Interface
The article compares two approaches to the description of ultrasound vocal tract images for application in a “silent speech interface,” one based on tongue contour modeling, a...
Thomas Hueber, Guido Aversano, Gérard Choll...