Ncr Corporation

James M Avery

Elmer A Hoyer

Madhu C Patel

A system for converting known speech segments into machine storable binary signals for the purpose of later attempting a match between a stored signal and an incoming signal using autocorrelation techniques. Through the use of a clipper and a sample and hold register, the system converts an incoming speech signal into a bit stream signal. Two successive groups of bits called frames are stored in separate registers. A bit-by-bit correlation is performed on the bits stored in the separate registers and a counter is indexed as a function of the correlation. A memory is provided for maintaining a record of the counts associated with each speech segment for later attempting computer pattern matching against received unknown speech segments.

Binary autocorrelation processor

A portable transaction processing calculator has a keyboard and a display window along with slots for holding at least a pair of credit cards. One of the cards includes storage means therein and is electrically connected with the calculator, and another card has optical or other readable data thereon and readable by optical or other equipment. A selector switch on the calculator selects one of four different operations.

Pocket calculator with credit card controller and dispenser

A method and implementation apparatus for converting analog signals, such as speech signals, into digital data signals, with improved fidelity by the use of dithering techniques coupled with amplitude clipping and filtering operations.

Digital processor for speech signals

The present invention relates to a speech recognition system and the method therefor, which analyzes a sampled clipped speech signal for identifying a spoken utterance. An input signal representative of the spoken utterance is passed through a clipper to generate a clipped input signal. A sampler generates a plurality of discrete binary values, each discrete binary value corresponding to a sample value of the clipped input signal. A processor then analyzes the plurality of sample values thereby identifying the spoken utterance. Analysis includes determining linear prediction coefficients of the autocorrelation function of speech utterences.

Growing community of inventors

Austin, TX, United States of America

James M Avery