Abstract: The vocabulary size of a speech recognizer for a large task is reduced by providing a recognizer only for the most common vocabulary items. Uncommon items are catered for by providing aliases from the common items. This allows accuracy to remain high while also allowing uncommon items to be recognized when necessary.

Abstract: This invention relates to an improved method and apparatus for speaker recognition. In this invention, prior to comparing feature vectors derived from speech with a stored reference model the feature vectors are processed by applying a speaker dependent transform which matches the characteristics of a particular speaker's vocal tract. Features derived from speech which has very dissimilar characteristics to those of the speaker on which the transform is dependent may be severely distorted by the transform, whereas features from speech which has similar characteristics to those of the speaker on which the transform is dependent will be distorted far less.

Abstract: In this invention vocabulary size of a speech recognizer for a large task is reduced by providing a recognizer only for the most common vocabulary items. Uncommon items are catered for by providing aliases from the common items. This allows accuracy to remain high while also allowing uncommon items to be recognized when necessary.

Abstract: Pattern recognition apparatus uses a recognition processor for processing an input signal to indicate its similarity to allowed sequences of reference patterns to be recognised. A speech recognition processor includes a classification arrangement to identify a sequence of patterns corresponding to said input signal and for repeatedly partitioning the input signal into a speech-containing portion and, preceding and/or following said speech-containing portion, noise or silence portions. A noise model generator is provided to generate a pattern of the noise or silence portion, for subsequent use by said classification means for pattern identification purposes. The noise model generator may generate a noise model for each noise portion of the input signal, which may be used to adapt the reference patterns.