5th International Conference on Spoken Language Processing
We describe a large-scale investigation of dependency grammar language models. Our work includes several significant departures from earlier studies, notably a larger training corpus, improved model structure, different feature types, new feature selection methods, andmore coherent training and test data. We report word error rate (WER) results of a speech recognition experiment, in which we used these models to rescore the output of the IBM speech recognition system.
Bibliographic reference. Berger, Adam / Printz, Harry (1998): "Recognition performance of a large-scale dependency grammar language model", In ICSLP-1998, paper 0679.