In a speech recognition system disclosed herein, acoustic speech waveforms are initially analyzed to obtain, at successive sample times, digital frames of speech information. This initial analysis may, for example, be performed by multi-channel filtering or linear predictive encoding. Stored in the apparatus is a list of representative standard frames, represented by coded indices, together with a table of difference values which represent the vector distances between each standard frame in the ...

Apparatus for recognizing a target such as a ship comprises a radar for successively sweeping the target to obtain input data representing the return amplitude from different target angles; a filter for selecting from the input data those significant ranges at which there is a significantly high amplitude; and a range difference compiler for identifying the frequency of occurrence of each of several range differences between pairs of the significant ranges, the most common range differences (exp...

In a speech recognizer, for recognizing unknown utterances in isolated-word speech or continuous speech, improved recognition accuracy is obtained by augmenting the usual spectral representation of the unknown utterance with a dynamic component. A corresponding dynamic component is provided in the templates with which the spectral representation of the utterance is compared. In preferred embodiments, the representation is mel-based cepstral and the dynamic components comprise vector differences ...

A speech recognition system comprises a recogniser (2) for receiving speech signals from users. The recogniser (2) compares each received word with templates of words stored in a reference template store (3) and flags each template that corresponds most closely to a received word. The flagged templates are stored in a template store (11). The recogniser (2) compares the speech pattern from a given user of a second utterance of a word for which a flagged template is already stored in the template...

An electronic recognition unit indicates that a flow of received information is starting when a desired bi-phased pulsed ratio signal starts to be received. The recognition unit discriminates against both noise and spurious radio signals. Desired signals are made recognizable by reversing, upon transmission, the phase of the carrier for a prescribed pattern of pulses. This technique prevents responding to unqualified continuous-wave signals. The relative phases of adjacent radio-frequency pulses...

A method of character recognition includes detecting a union of characters, preprocessing the union of characters, comparing the preprocessed union of characters with one or more template symbols, and applying a decision rule in order to either reject a template symbol or decide that the template symbol is included in the union of characters. Preprocessing the union of characters involves representing the union of characters as one or more curves, and parameterising said curve or curves, and reg...

A recognition system (10) incorporates a filterbank analyser (16) producing successive data vectors of energy values for twenty-six frequency intervals in a speech signal. A unit (18) compensates for spectral distortion in each vector. Compensated vectors undergo a transformation into feature vectors with twelve dimensions and are matched with hidden Markov model states in a computer (24). Each matched model state has a mean value which is an estimate of the speech feature vector. A match invert...

This invention relates to a method and apparatus for recognizing a script written character. The character is entered using character entering means and digitised by appropriate means. The digitised character is then stored in, for example, a memory. Codes representing topological features of the character are extracted from the character, then the topological features of the character are compared with a set of reference topological features stored in a memory. Each of the set of reference char...

A recognition process for handwritten characters, including generating sub-segments representing at least one character stroke, the sub-segments each having a boundary enclosing the at least one stroke of the sub-segment, merging the sub-segments when the distance between centroids of the sub-segments are less than a predetermined threshold, and generating segments representing possible characters from the sub-segments.

Speech recognition in which the log probabilities of the null and alternative hypothesis are computed for an input speech sample by comparison with specific stored speech vocabularies/grammars and with general speech characteristics. The difference in probabilities is normalized by the magnitude of the null hypothesis to derive a likelihood factor which is compared with a rejection threshold that is utterance-length dependent. Advantageously, a high-order polynomial representation of the rejecti...