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...
Lukas Burget, Petr Schwarz, Mohit Agarwal, Pinar A...
Minimum phone error (MPE) acoustic parameter estimation involves calculation of edit distances (errors) between correct and incorrect hypotheses. In the context of large vocabulary...
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 ...
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...
Xunying Liu, Mark John Francis Gales, Jim L. Hiero...
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...
Vikramjit Mitra, Hosung Nam, Carol Y. Espy-Wilson,...