Bayesian Language Model Interpolation for Mobile Speech Input
Venue
Interspeech 2011, pp. 1429-1432
Publication Year
2011
Authors
BibTeX
Abstract
This paper explores various static interpolation methods for approximating a single
dynamically-interpolated language model used for a variety of recognition tasks on
the Google Android platform. The goal is to find the statically-interpolated
firstpass LM that best reduces search errors in a two-pass system or that even
allows eliminating the more complex dynamic second pass entirely. Static
interpolation weights that are uniform, prior-weighted, and the maximum likelihood,
maximum a posteriori, and Bayesian solutions are considered. Analysis argues and
recognition experiments on Android test data show that a Bayesian interpolation
approach performs best.
