Sciweavers

NAACL
1994
14 years 1 months ago
High-Accuracy Large-Vocabulary Speech Recognition Using Mixture Tying and Consistency Modeling
Improved acoustic modeling can significantly decrease the error rate in large-vocabulary speech recognition. Our approach to the problem is twofold. We first propose a scheme that...
Vassilios Digalakis, Hy Murveit
ICASSP
2008
IEEE
14 years 7 months ago
Corrected tandem features for acoustic model training
This paper describes a simple method for significantly improving Tandem features used to train acoustic models for large-vocabulary speech recognition. The linear activations at ...
Arlo Faria, Nelson Morgan