We introduce a hierarchical statistical language model, represented as a collection of local models plus a general sentence model. We provide an example that mixes a trigram general model and a PFSA local model for the class of decimal numbers, described in terms of sub-word units (graphemes). This model practically extends the vocabulary of the overall model to an infinite size, but still has better performance compared to a word-based model. Using in-domain language model adaptation experiments, we show that local models can encode enough linguistic information, if well trained, that they may be ported to new language models without re-estimation.

This thesis deals with the problem of Out-Of-Vocabulary words in speech recognition. The standard response of speech recognition systems whenever they encounter such OOV words is to (silently) misrecognize them without issuing any warning to the user. In order to avoid this undesired behaviour, two different strategies are proposed. The first strategy consists in preventing the problem, i.e. the occurrence of OOV words, and this thesis presents two ways of doing that. First, the system vocabulary is optimized using information extracted from other corpora and application domains, such that the number of expected OOV words be minimized. Using this method, the vocabulary coverage was significantly improved, especially for small vocabularies. The second method of reducing the number of OOV words consists of redefining the concept of "word" based on morphological considerations. In particular, compound words are decomposed into their constituent parts, which are used as the lexical recogni...