Getting More Mileage from Web Text Sources for Conversational Speech Language Modeling using Class-Dependent Mixtures

Sources of training data suitable for language modeling of conversational speech are limited. In this paper, we show how training data can be supplemented with text from the web filtered to match the style and/or topic of the target recognition task, but also that it is possible to get bigger performance gains from the data by using class-dependent interpolation of N-grams.

• Type: Conference
• Year: 2003
• Where: NAACL
• Authors: Ivan Bulyko, Mari Ostendorf, Andreas Stolcke
• Keywords: NAACL 2003, NAACL 2007, Style And/or Topic, Target Recognition Task, Training Data