Paper: Applying a Grammar-Based Language Model to a Simplified Broadcast-News Transcription Task

ACL ID P08-1013
Title Applying a Grammar-Based Language Model to a Simplified Broadcast-News Transcription Task
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
Authors

We propose a language model based on a precise, linguistically motivated grammar (a hand-crafted Head-driven Phrase Structure Grammar) and a statistical model estimating the probability of a parse tree. The language model is applied by means of an N-best rescor- ing step, which allows to directly measure the performance gains relative to the baseline sys- tem without rescoring. To demonstrate that our approach is feasible and beneficial for non-trivial broad-domain speech recognition tasks, we applied it to a simplified German broadcast-news transcription task. We report a significant reduction in word error rate com- pared to a state-of-the-art baseline system.