Tied Mixtures in the Lincoln Robust CSR
MASSACHUSETTS INST OF TECH LEXINGTON LINCOLN LAB
Pagination or Media Count:
HMM recognizers using either a single Gaussian or a Gaussian mixture per state have been shown to work fairly well for 1000-word vocabulary continuous speech recognition. However, the large number of Gaussians required to cover the entire English language makes these systems unwieldy for large vocabulary tasks. Tied mixtures offer a more compact way of representing the observation pdfs. We have converted our independent mixture systems to tied mixtures and have obtained mixed results a 13 improvement in speaker-dependent recognition without cross-word triphone models, but no improvement in our speaker-dependent system with cross-word boundary triphone models or in our speaker-independent system. There is also a reduction in CPU requirements during recognition--but this is counter-balanced by an increase during training. This paper also includes a comment on the validity of the DARPA programs evaluation test system comparisons.
- Voice Communications