Integrating Language Models with Speech Recognition

M. P. Harper, L. H. Jamieson, C. D. Mitchell, G. Ying, S. Potisuk, P. N. Srinivasan, R. Chen, C. B. Zoltowski, L. L. McPheters, B. Pellom, and R. A. Helzerman 1285 The Electrical Engineering Building School of Electrical Engineering Purdue University West Lafayette, IN 47907-1285 fharper,lhj,cdm,sgsying,pong,pramila,ruxin,bauercar,mcpheter,pellom,[email protected] Abstract The question of how to integrate language models with speech recognition systems is becoming more important as speech recognition technology matures. For the purposes of this paper, we have classi ed the level of integration of current and past approaches into three categories: tightly-coupled, loosely-coupled, or semicoupled systems. We then argue that loose coupling is more appropriate given the current state of the art and given that it allows one to measure more precisely which components of the language model are most important. We will detail how the speech component in our approach interacts with the language model and discuss why we chose our language model.