Sciweavers

302 search results - page 39 / 61
» Reservoir-based techniques for speech recognition
Sort
View
FLAIRS
2008
13 years 10 months ago
Learning Dynamic Naive Bayesian Classifiers
Hidden Markov models are a powerful technique to model and classify temporal sequences, such as in speech and gesture recognition. However, defining these models is still an art: ...
Miriam Martínez, Luis Enrique Sucar
ICASSP
2011
IEEE
12 years 11 months ago
Whole word discriminative point process models
This paper introduces a discriminative extension to whole-word point process modeling techniques. Meant to circumvent the strong independence assumptions of their generative prede...
Aren Jansen
ICASSP
2011
IEEE
12 years 11 months ago
NAP for high level language identification
Varying channel conditions present a difficult problem for many speech technologies such as language identification (LID). Channel compensation techniques have been shown to sig...
Fred S. Richardson, William M. Campbell
NAACL
2003
13 years 9 months ago
Comma Restoration Using Constituency Information
Automatic restoration of punctuation from unpunctuated text has application in improving the fluency and applicability of speech recognition systems. We explore the possibility t...
Stuart M. Shieber, Xiaopeng Tao
ICASSP
2008
IEEE
14 years 2 months ago
Filter bank design based on minimization of individual aliasing terms for minimum mutual information subband adaptive beamformin
This paper presents new filter bank design methods for subband adaptive beamforming. In this work, we design analysis and synthesis prototypes for modulated filter banks so as t...
Ken'ichi Kumatani, John W. McDonough, S. Schachl, ...