We propose a method that uses a filler prediction model for building a language model that includes fillers from a corpus without fillers. In our method, a filler prediction model is trained from a corpus that does not cover domain-relevant topics. It recovers fillers in inexact transcribed corpora in the target domain, and then a language model that includes fillers is built from the corpora. The results of an evaluation of the Japanese National Diet Record showed that a model using our method achieves higher recognition performance than conventional ones.
Bibliographic reference. Ohta, Kengo / Tsuchiya, Masatoshi / Nakagawa, Seiichi (2008): "Evaluating spoken language model based on filler prediction model in speech recognition", In INTERSPEECH-2008, 1558-1561.