Adding Robustness to Language Models for Spontaneous Speech Recognition

Compared to dictation systems, recognition systems for spontaneous speech still perform rather poorly. An important weakness in these systems is the statistical language model, mainly due to the lack of large amounts of stylistically matching training data and to the occurrence of disfluencies in the recognition input. In this paper we investigate a method for improving the robustness of a spontaneous language model by flexible manipulation of the prediction context when disfluencies occur. In the case of repetitions, we obtained significantly better recognition results on a benchmark Switchboard test set.