Speaker Verification Based on Log-Likelihood Score Normalization

Due to differences in the distribution of scores for different trials, the performance of a speaker verification system will be seriously diminished if raw scores are directly used for detection with a unified threshold value. As such, the scores must be normalized. To tackle the shortcomings of score normalization methods, we propose a speaker verification system based on log-likelihood normalization (LLN). Without a priori knowledge, LLN increases the separation between scores of target and non-target speaker models, so as to improve score aliasing of “same-speaker” and “different-speaker” trials corresponding to the same test speech, enabling better discrimination and decision capability. The experiment shows that LLN is an effective method of scoring normalization.

A New Speaker Verification Method with Global Speaker Model and Likelihood Score Normalization

In this paper a new text-independent speaker verification method GSMSV is proposed based on likelihood score normalization. In this novel method a global speaker model is established to represent the universal features of speech and normalize the likelihood score. Statistical analysis demonstrates that this normaliza- tion method can remove common factors of speech and bring the differences between speakers into prominence. As a result the equal error rate is decreased significantly, verification procedure is accelerated and system adaptability to speaking speed is improved.

Cross similarity measurement for speaker adaptive test normalization in text-independent speaker verification

Speaker adaptive test normalization （ATnorm） is the most effective approach of the widely used score normalization in text-flldependent speaker verification, which selects speaker adaptive impostor cohorts with an extra development corpus in order to enhance the recognition performance. In this paper, an improved implementation of ATnorm that can offer overall significant advantages over the original ATnorm is presented. This method adopts a novel cross similarity measurement in speaker adaptive cohort model selection without an extra development corpus. It can achieve a comparable performance with the original ATnorm and reduce the computation complexity moderately. With the full use of the saved extra development corpus, the overall system performance can be improved significantly. The results are presented on NIST 2006 Speaker Recognition Evaluation data corpora where it is shown that this method provides significant improvements in system performance, with relatively 14.4% gain on equal error rate （EER） and 14.6% gain on decision cost function （DCF） obtained as a whole.

Geostatistics for Spatial Uncertainty Characterization

Most geospatial phenomena can be interpreted probabilistically because we are ignorant of the biophysical proc- esses and mechanisms that have jointly created and observed events. This philosophy is important because we are certain about the phenomenon under study at sampled locations, except for measurement errors, but, in between the sampled, we become uncertain about how the phenomenon behaves. Geostatistical uncertainty characterization is to generate random numbers in such a way that they simulate the outcomes of the random processes that created the existing sample data. This set of existing sample is viewed as a partially sampled realization of that random function model. The random function＇s spa- tial variability is described by a variogram or covariance model. The realized surfaces need to honour sample data at their lo- cations, and reflect the spatial structure quantified by the variogram models. They should each reproduce the sample histo- gram representative of the whole sampling area. This paper will review the fundamentals in stochastic simulation by covering univariate and indicator techniques in the hope that their applications in geospatial information science will be wide-spread and fruitful.