Sciweavers

47 search results - page 8 / 10
» Discriminative Word Alignment by Linear Modeling
Sort
View
ICASSP
2009
IEEE
15 years 4 months ago
Training and adapting MLP features for Arabic speech recognition
Features derived from Multi-Layer Perceptrons (MLPs) are becoming increasingly popular for speech recognition. This paper describes various schemes for applying these features to ...
J. Park, Frank Diehl, M. J. F. Gales, Marcus Tomal...
NAACL
2010
14 years 8 months ago
Improved Models of Distortion Cost for Statistical Machine Translation
The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing sea...
Spence Green, Michel Galley, Christopher D. Mannin...
GW
2005
Springer
129views Biometrics» more  GW 2005»
15 years 3 months ago
Visual Sign Language Recognition Based on HMMs and Auto-regressive HMMs
Abstract. A sign language recognition system based on Hidden Markov Models(HMMs) and Auto-regressive Hidden Markov Models(ARHMMs) has been proposed in this paper. ARHMMs fully cons...
Xiaolin Yang, Feng Jiang, Han Liu, Hongxun Yao, We...
ICML
2010
IEEE
14 years 11 months ago
Conditional Topic Random Fields
Generative topic models such as LDA are limited by their inability to utilize nontrivial input features to enhance their performance, and many topic models assume that topic assig...
Jun Zhu, Eric P. Xing
ICASSP
2009
IEEE
15 years 4 months ago
Exploiting user feedback for language model adaptation in meeting recognition
We investigate language model (LM) adaptation in a meeting recognition application, where the LM is adapted based on recognition output from relevant prior meetings and partial ma...
Dimitra Vergyri, Andreas Stolcke, Gökhan T&uu...