Analyzing and predicting language model improvements

this paper, we study alternatives to perplexity for predicting language model performance, including other global features as well as a new approach that predicts, with a high correlation (0.96), performance differences associated with localized changes in language models given a recognition system. Experiments focus on the problem of augmenting in-domain Switchboard text with out-of-domain text from Wall Street Journal and Broadcast News that differ in both style and content from the in-domain data.