Syntactic language modeling with formal grammars

It has repeatedly been demonstrated that automatic speech recognition can benefit from syntactic information. However, virtually all syntactic language models for large-vocabulary continuous speech recognition are based on statistical parsers. In this paper, we investigate the use of a formal grammar as a source of syntactic information. We describe a novel approach to integrating formal grammars into speech recognition and evaluate it in a series of experiments. For a German broadcast news transcription task, the approach was found to reduce the word error rate by 9.7% (relative) compared to a competitive baseline speech recognizer. We provide an extensive discussion on various aspects of the approach, including the contribution of different kinds of information, the development of a precise formal grammar and the acquisition of lexical information.

► We integrate a formal grammar into a statistical speech recognizer.
► We show that formal grammars can significantly improve LVCSR on a broad-domain task.
► We evaluate and discuss various aspects of our approach.