Cross-language text-independent speaker identification

In this paper, we investigate the influence of the language on the text-independent speaker recognition. For this purpose, we have used several automatic text-independent speaker recognition methods (Multivariable Auto-Regression, Vector Quantization and Histogram Classifiers). To measure the effect of the language, we have applied these methods on the POLY-COST 250 multi-language database. Among the different experiments, we have seen that the speaker recognition performance has not been really affected if the language used during the training and the test is different.