253 search results - page 15 / 51 » Robust Speech Recognition Using Neural Networks and Hidden M... |
227
click to vote
ICDAR
2007
IEEE
15 years 12 months ago
2007
IEEE
The paper describes a lexicon driven approach for word recognition on handwritten documents using Conditional Random Fields(CRFs). CRFs are discriminative models and do not make a...
163
click to vote
DAGM
2003
Springer
15 years 11 months ago
2003
Springer
In this paper we address the problem of building a good speech recognizer if there is only a small amount of training data available. The acoustic models can be improved by interpo...
203
click to vote
ICDAR
2011
IEEE
14 years 5 months ago
2011
IEEE
—To cope with the tremendous variations of writing styles encountered between different individuals, unconstrained automatic handwriting recognition systems need to be trained on...
178
click to vote
PR
2011
15 years 18 days ago
2011
The Student’s-t hidden Markov model (SHMM) has been recently proposed as a robust to outliers form of conventional continuous density hidden Markov models, trained by means of t...
145
click to vote
NAACL
1994
15 years 7 months ago
1994
In addressing the problem of achieving high-accuracy real-time speech recognition systems, we focus on recognizing speech from ARPA's20,000-word Wall Street Journal (WSJ) tas...