55 search results - page 6 / 11 » Large vocabulary continuous speech recognition with context-... |
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...
ICASSP
2009
IEEE
14 years 2 months ago
2009
IEEE
We introduce a direct model for speech recognition that assumes an unstructured, i.e., flat text output. The flat model allows us to model arbitrary attributes and dependences o...
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...
ICMCS
2006
IEEE
14 years 1 months ago
2006
IEEE
In this paper the optimal filter-bank design method based on the Minimum Phone Error (MPE) criteria is investigated. We use Gaussian type filter bank for optimization and variou...
FTSIG
2007
13 years 7 months ago
2007
Hidden Markov Models (HMMs) provide a simple and effective framework for modelling time-varying spectral vector sequences. As a consequence, almost all present day large vocabula...