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...
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...
M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schl...
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 ...
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,...