The speech recognizer incorporates a language model that reduces the number of acoustic pattern matching sequences that must be performed by the recognizer. The language model is based on knowledge of a pre-defined set of syntactically defined content and includes a data structure that organizes the...http://www.google.de/patents/US6182039?utm_source=gb-gplus-sharePatent US6182039 - Method and apparatus using probabilistic language model based on confusable sets for speech recognition
