Words are added to a speech recognition system vocabulary during user dictation by (a) extracting, from a multi-word user utterance, speech frames that correspond to each one of the one or more new words; and (b) building speech models for the one or more new words using the extracted speech...http://www.google.com.au/patents/US5765132?utm_source=gb-gplus-sharePatent US5765132 - Building speech models for new words in a multi-word utterance
