36 search results - page 4 / 8 » Discriminative training of hierarchical acoustic models for ... |
INTERSPEECH
2010
13 years 2 months ago
2010
Neural network language models (NNLM) have become an increasingly popular choice for large vocabulary continuous speech recognition (LVCSR) tasks, due to their inherent generalisa...
TASLP
2010
13 years 2 months ago
2010
Minimum phone error (MPE) acoustic parameter estimation involves calculation of edit distances (errors) between correct and incorrect hypotheses. In the context of large vocabulary...
INTERSPEECH
2010
13 years 2 months ago
2010
In large vocabulary continuous speech recognition, decision trees are widely used to cluster triphone states. In addition to commonly used phonetically based questions, others hav...
CSL
2004
Springer
13 years 7 months ago
2004
Springer
Recently various techniques to improve the correlation model of feature vector elements in speech recognition systems have been proposed. Such techniques include semi-tied covaria...
ICASSP
2010
IEEE
13 years 7 months ago
2010
IEEE
We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...