28 search results - page 2 / 6 » Improving speech recognition by explicit modeling of phone d... |
ICASSP
2010
IEEE
13 years 5 months ago
2010
IEEE
Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approa...
TASLP
2010
12 years 12 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
2010
IEEE
13 years 5 months ago
2010
IEEE
This paper addresses the problem of discriminative training of language models that does not require any transcribed acoustic data. We propose to minimize the conditional entropy ...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
One important issue in designing state-of-the-art LVCSR systems is the choice of acoustic units. Context dependent (CD) phones remain the dominant form of acoustic units. They can...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
Previously we have proposed different models for estimating articulatory gestures and vocal tract variable (TV) trajectories from synthetic speech. We have shown that when deploye...