5 search results - page 1 / 1 » Generation of Synthetic Training Data for an HMM-based Handw... |
ICDAR
2003
IEEE
13 years 10 months ago
2003
IEEE
A perturbation model for generating synthetic textlines from existing cursively handwritten lines of text produced by human writers is presented. Our purpose is to improve the per...
PRL
2000
13 years 5 months ago
2000
: In this study, we introduce a set of one-dimensional features to represent two dimensional shape information for HMM (Hidden Markov Model) based handwritten optical character rec...
ICDAR
2009
IEEE
13 years 3 months ago
2009
IEEE
In this paper, we present a novel approach for incorporating structural information into the hidden Markov Modeling (HMM) framework for offline handwriting recognition. Traditiona...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
Previously we have proposed different models for estimating articulatory gestures and vocal tract variable (TV) trajectories from synthetic speech. We have shown that when deploye...
LRE
2006
13 years 5 months ago
2006
When building a new spoken dialogue application, large amounts of domain specific data are required. This paper addresses the issue of generating in-domain training data when litt...