9 search results - page 2 / 2 » Investigation of acoustic units for LVCSR systems |
TASLP
2008
13 years 4 months ago
2008
In this paper we investigate the combination of complementary acoustic feature streams in large vocabulary continuous speech recognition (LVCSR). We have explored the use of acoust...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Polish is a synthetic language with a high morpheme-perword ratio. It makes use of a high degree of inflection leading to high out-of-vocabulary (OOV) rates, and high Language Mo...
ACL
2008
13 years 6 months ago
2008
Accurate unsupervised learning of phonemes of a language directly from speech is demonstrated via an algorithm for joint unsupervised learning of the topology and parameters of a ...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
In context-dependent acoustic modeling, it is important to strike a balance between detailed modeling and data sufficiency for robust estimation of model parameters. In the past,...