160 search results - page 18 / 32 » Exploiting contextual information for improved phoneme recog... |
CVPR
2011
IEEE
13 years 3 months ago
2011
IEEE
We present an approach to jointly solve the segmentation and recognition problem using a multiple segmentation framework. We formulate the problem as segment selection from a pool...
ICDAR
2009
IEEE
14 years 2 months ago
2009
IEEE
This paper presents a rule-based approach that utilizes some types of contextual information to improve the accuracy of handwritten mathematical expression(ME) recognition. Mining...
NIPS
2008
13 years 9 months ago
2008
Language and image understanding are two major goals of artificial intelligence which can both be conceptually formulated in terms of parsing the input signal into a hierarchical ...
CHINZ
2008
ACM
13 years 9 months ago
2008
ACM
As performance gains in automatic speech recognition systems plateau, improvements to existing applications of speech recognition technology seem more likely to come from better u...
COLING
2000
13 years 9 months ago
2000
Multi-word terms are traditionally identified using statistical techniques or, more recently, using hybrid techniques combining statistics with shallow linguistic information. Al)...