METHOD AND APPARATUS FOR SPEECH RECOGNITION ADAPTEMETHOD AND APPARATUS FOR SPEECH RECOGNITION ADAPTED TO AN INDIVIDUAL SPEAKER D TO AN INDIVIDUAL SPEAKER

摘要

A method and apparatus for automatic recognition of speech adapts to a particular speaker by using adaptation data to develop a transformation through which speaker independent models are transformed into speaker adapted models. The speaker adapted models are then used for speaker recognition and achieve better recognition accuracy than non-adapted models. In a further embodiment, the transformation-based adaptation technique is combined with a known Bayesian adaptation technique.