A method of automatic speaker identification based on the physiology of the vocal apparatus and essentially independent of the spoken message has been developed. Power spectra produced during nasal phonation are transformed and statistically matched. In experiments involving the identification of individual speakers out of a population of 10 speakers, an average identification accuracy of 97% was obtained. With an experimental population of 30 speakers, identification accuracy was 93%. The procedure is outlined, and the experimental evaluation of it is described.

The circuit described here is used to vibrate a listener's chair. It consists of a bandpass filter tuned to cover roughly the fundamental frequency range of speech and a rectifier/low-pass combination to measure the amplitude level in the filtered band. A voice discriminator consists of a comparator that indicates when the bandpass energy is greater than a certain fraction of the overall energy. The switched and amplified low-pass portion of the signal is used to vibrate the seat of a movicgoer for heightened effects.m DLR 4,624,009 43.72.Ne SIGNAL PATTERN ENCODER AND CLASSIFIER James W. Glenn and Joseph C. Brown, assignors to Figpie International, Incorporated 18 November 1986 {Class 381/43}; filed 2 May 1980