Abstract: An unknown segment such as a spoken digit in a continuous speech signal is recognized as a previously identified speech segment by deriving a set of test linear prediction characteristic signals from the voiced interval of the unknown segment. The test signals are time aligned to the average voiced interval of repetitions of each of a plurality of identified speech segments for which average reference voiced interval linear prediction characteristic signals were previously generated. The correspondence between the aligned test signals and the reference signals is determined. The unknown speech segment is identified as the reference segment having the closest correspondence with the unknown segment. Features of the invention include: voiced-region parameter signals, and classification and consistency detection; and determining means and variances of voiced-region parameters from a plurality of speakers utilized for the correspondence arrangements.

Abstract: This speaker recognition system offers improved recognition by comparing the mean and variance of an unknown (test) speaker's Orthogonal Parameter signals versus those of previously-stored known (reference) speakers. The unknown speaker's Orthogonal Parameters represent his hypothesized identity because his original speech linear prediction coefficients are transformed into his set of Orthogonal Parameters using the stored (reference) transformation coefficients of each of the previously-recorded known speakers.