HISTOGRAM NORMALIZATION OF SPEECH FEATURES FOR SPEAKERS’ VERIFICATION
Read the full article
The article provides a brief description of the algorithm for histogram normalization of speech features for speakers’ verification. Results of verification tests with different parameters and modes of normalization are presented. Obtained data make it possible to conclude about the effectiveness of the speech features normalization for increasing the performance of speakers’ verification. Optimal parameters of the normalization algorithm were found.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License