Statistical feature language model

Statistical language models are widely used in automatic speech recognition in order to constrain the decoding of a sentence. Most of these models derive from the classical n-gram paradigm. However, the production of a word depends on a large set of linguistic features : lexical, syntactic, semantic, etc. Moreover, in some natural languages the gender and number of the left context affect the production of the next word. Therefore, it seems attractive to design a language model based on a variety of word features. We present in this paper a new statistical language model, called Statistical Feature Language Model, SFLM, based on this idea. In SFLM a word is considered as an array of linguistic features, and the model is defined in a way similar to the n-gram model. First experiments were carried out for French by using only two features and showed improvement in terms of perplexity and Shannon game.