Generalized linear interpolation of language models
Bo-June Paul Hsu · 2007
Despite the prevalent use of model combination techniques to improve speech recognition performance on domains with limited data, little prior research has focused on the choice of the actual interpolationmodel. For merging language models, the most popular approach has been the simple linear interpolation. In this work, we propose a generalization of linear interpolation that computes context-dependent mixture weights from arbitrary features. Results on a lecture transcription task yield up to a 1.0% absolute improvement in recognition word error rate (WER).