INTERDEPENDENCE OF LANGUAGE MODELS AND DISCRIMINATIVE TRAINING

Abstract

In this paper, the interdependence of language models and discriminative training for large vocabulary speech recognition is investigated. In addition, a constrained recognition approach using word graphs is presented for the efficient determination of alternative word sequences for discriminative training. Experiments have been carried out on the ARPA Wall Street Journal corpus. The recognition results for MMI training show a significant dependence on the context length of the language model used for training. Best results were obtained using a unigram language model for MMI training. No significant correlation has been observed between the language model choice for training and recognition. 1.