Google Research

Bayesian Language Model Interpolation for Mobile Speech Input

Interspeech 2011, pp. 1429-1432


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.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work