In this paper a histogram enhancement technique is presented in order to improve the robustness of text-independent speaker verification systems. The technique transforms the features extracted from speech such that the contrast of their histogram is enhanced. Experiments showed significant improvements for this technique compared to standard techniques both in clean testing environments, and in the presence of additive noise.
Bibliographic reference. Kwon, C. H. / Choi, J. K. / Ambikairajah, Eliathamby (2008): "Performance improvement of text-independent speaker verification systems based on histogram enhancement in noisy environments", In INTERSPEECH-2008, 1901-1904.