Large-vocabulary speech recognition in specialized domains
Hugo Le Chevalier, Charles Ingold, Coltin Kunz, Cristopher Moore, C. Roven, J.P. Yamron, B. Baker, Paul G. Bamberg, S. Bridle, Thomas Robert Bruce, A. Weader · 2002
We report on research into the discrete-word speech recognition performance of several specialized language models optimized for four large domains of professional discourse. We describe the construction of these models and report perplexity and recognition results for each of the specialized domains. The data indicate that such specialization may significantly improve performance both before and after adaptation.