Abstract
In SRI’s language modeling experiments for the Hub4 domain, three basic approaches were pursued: interpolating multiple models estimated from Hub4 and non-Hub4 training data, adapting the language model (LM) to the focus conditions, and adapting the LM to different topic types. n the first approach, we built separate LMs for the closely transcribed Hub4 material (acoustic training transcripts) and the loosely transcribed Hub4 material (LM training data), as well as the North-American Business News (NABN) and Switchboard training data, projected onto the Hub4 vocabulary. By interpolating the probabilities obtained from these models, we obtained a 20 percent reduction in perplexity and a 1.8 percent reduction in word error rate, compared to a baseline Hub4-only language model. […]
Share this
