Informatica

The problem of speaker identification is investigated. Basic segments – pseudostationary intervals of voiced sounds are used for identification. The identification is carried out, comparing average distances between an investigative and comparatives. Coefficients of the linear prediction model (LPC) of a vocal tract, cepstral coefficients and LPC coefficients of an excitation signal are used for identification as features. Three speaker identification methods are presented. Experimental investigation of their performance is discussed.

The use of vector quantization for speaker identification is investigated. This method differs from the known methods in that the number of centroids is not doubled but increases by 1 at every step. This enables us to obtain identification results at any number of centroids. This method is compared experimentally with the method (Lipeika and Lipeikienė, 1993a, 1993b), where feature vectors of investigative and comparative speakers are compared directly.

Speaker identification problem is investigated. The identification is carried out comparing feature vectors (parameters of LPC model) of the “criminal” and “suspicious” speakers. Both likelihood ratio and cepstral distances are used for comparing feature vectors. The feature vectors are extracted from pseudostationary parts of speech utterances. The identification approach is suitable for text-dependent and text-independent identification. Experimental results illustrate the performance of the algorithm.