Utterance data that includes at least a small amount of manually transcribed data is provided. Automatic speech recognition is performed on ones of the utterance data not having a corresponding manual transcription to produce automatically transcribed utterances. A model is trained using all of the manually...http://www.google.co.uk/patents/US20060190253?utm_source=gb-gplus-sharePatent US20060190253 - Unsupervised and active learning in automatic speech recognition for call classification
