tech,6-1-N03-2003,bq | <term> training data </term> suitable for <term> | language modeling | </term> of <term> conversational speech </term> | #3020 Sources of training data suitable for language modeling of conversational speech are limited. |
tech,27-2-N03-2003,bq | and/or <term> topic </term> of the target <term> | recognition task | </term> , but also that it is possible to | #3055 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. |