Ncr Corporation

Nortel Networks Corporation

Northern Telecom Limited

Hung Shun Ma

Robert B Nally

James F Akister

Marco Petroni

A method and apparatus for compressing and decompressing an audio signal. The apparatus comprises an input for receiving an audio signal derived from a spoken utterance, the audio signal being contained into a plurality of successive data frames. A data frame holding a certain portion the audio signal is processed to generate a feature vector including a plurality of discrete elements characterizing at least in part the portion of the audio signal encompassed by the frame, the elements being organized in a certain sequence. The apparatus makes use of a compressor unit having a grouping processor for grouping elements of the feature vector into a plurality of sub-vectors on the basis of a certain grouping scheme, at least one of the sub-vectors including a plurality of elements from the feature vector, the plurality of elements being out of sequence relative to the certain sequence. The plurality of sub-vectors are then quantized by applying a vector quantization method.

Split-vector quantization for speech signal involving out-of-sequence regrouping of sub-vectors

Methods and systems consistent with the present invention enroll a candidate phrase uttered by a user in a dictionary having at least one previously enrolled phrase. The system receives utterances of the candidate phrase and determines whether the first utterance is confusingly similar to a previously enrolled phrase and whether they are consistent with each other. The system then enrolls the candidate phrase in the dictionary according to these determinations.

Recognition system for determining whether speech is confusing or

A method and a system for extracting character information from a signal matrix of gray level picture elements which compares pixel elements positioned in annular rings around a central pixel of interest to determine neighbor pair occurrences for purposes of eliminating spurious signals and for establishing a threshold for each document read which is used to eliminate undesired signals from the signal matrix.

Adaptive character extraction method and system

A method and system of matching first and second waveforms, each having identifiable features, for identification purposes. The method includes the steps of obtaining from the first waveforms significant said identifiable features having values and locations with respect to a starting point of the associated said first waveform, with the significant identifiable features being obtained according to the predetermined criteria; utilizing values and locations of the significant identifiable features of a first waveform to search in predetermined locations for anticipated corresponding identifiable features in a second waveform; determining the values and locations of the identifiable features, if any, found in the predetermined locations; and comparing the values and locations from the determining step with the values and locations of the significant identifiable features of a first waveform according to second predetermined criteria to determine whether or not the second waveform matches a first waveform. The system includes a data acquisition module for obtaining the significant identifiable features mentioned, and a matching module for utilizing the significant identifiable features of the first waveforms to effect the comparing step mentioned.

Growing community of inventors

Beaconsfield, Canada

Hung Shun Ma