Informatica

New text independent speaker identification method is presented. Phase spectrum of all-pole linear prediction (LP) model is used to derive the speech features. The features are represented by pairs of numbers that are calculated from group delay extremums of LP model spectrum. The first component of the pair is an argument of maximum of group delay of all pole LP model spectrum and the second is an estimation of spectrum bandwidth at the point of spectrum extremum. A similarity metric that uses group delay features is introduced. The metric is adapted for text independent speaker identification with general assumption that test speech channel may contain multiple speakers. It is demonstrated that automatic speaker recognition system with proposed features and similarity metric outperforms systems based on Gaussian mixture model with Mel frequency cepstral coefficients, formants, antiformants and pitch features.

This paper presents a method of minutiae based fingerprint matching that is robust to deformations and does not do fingerprint alignment. It concentrates on comparing rotation and translation invariant local structures defined by minutiae point and its neighboring minutiae points. Then the collection of most probable correspondences of matched minutiae is found. Finally, the local structures of higher order are validated. All three steps are completely rotation and translation invariant, robust to nonlinear deformations and do not use any fingerprint alignment. Experimental results on publicly available as well as internal databases show an improved performance of the proposed method in comparison with the traditional minutiae based algorithms that perform fingerprint registration.