Text-dependent speaker recognition using the information in the higher frequency band

In previous studies, the speaker individual information in the higher frequency band has been almost neglected. Therefore, we investigate the speaker characteristics in the higher frequency band and the effects of using them for speaker recognition. This paper presents the results of speaker identification experiments performed in a text-dependent mode using various frequency bands. Moreover, we propose a new distance measure combining the lower and the higher frequency bands. The experiment results show effectiveness of using the individual information in the higher frequency band to improve the speaker recognition performance.<<ETX>>