This paper is intended to introduce a graduate student to the speaker verification problem. Knowledge of pioneer work, as well as real methods overview, clears the path into deeper investigation. A list of useful references and books provides further orientation. The panorama is not complete if practical considerations are not taken into account: corpora, assessment of detection performance, sp...

Two approaches are presented for non-linear PLDA to be used in speaker verification. In NIST 2010 speaker recognition evaluation (SRE) tests under DET-5 conditions, the two methods and particularly their combination provided significant improvements in equal error rates and minDCF values over a standard PLDA scheme. The proposed schemes were also applied within a speaker verification system tha...

Jitter and shimmer are measures of the fundamental frequency and amplitude cycle-to-cycle variations, respectively. Both features have been largely used for the description of pathological voices, and since they characterise some aspects concerning particular voices, they are expected to have a certain degree of speaker specificity. In the current work, jitter and shimmer are successfully used ...

Combined software and hardware research has been conducted in the Speaker Verification area, where a Speaker Verification application has been developed in JAVA, based on Vector Quantizing, VQ, and Mel Frequency Cepstral Coefficients, MFCC’s. Extended research has been carried out on the Fourier Transform, since it is one of the parts demanding most computational power in the Speaker Verificati...

In this paper a new text-independent speaker verification method is proposed based on likelihood score normalization and the global speaker model, which is established to represent the universal features of speech and environment, and to normalize the likelihood score. As a result the equal error rates are decreased significantly, verification procedure is accelerated and system adaptability is...