Speaker Discrimination Using Long-Term Spectrum of Speech

Abstract

In this article, a specific long-term speech spectrum was investigated with respect to its use for speaker recognition. The long-term spectrum was calculated by means of second-order linear prediction using the average autocorrelation coefficients. Four subbands with the most discriminative capability were selected for speaker recognition. These subbands involve the frequencies of 0-1.2 kHz in total. The best recognition rates, i.e. 91.7% on complete speech and 100% on voiced speech, were achieved in optimal paired subbands.In this article, a specific long-term speech spectrum was investigated with respect to its use for speaker recognition. The long-term spectrum was calculated by means of second-order linear prediction using the average autocorrelation coefficients. Four subbands with the most discriminative capability were selected for speaker recognition. These subbands involve the frequencies of 0-1.2 kHz in total. The best recognition rates, i.e. 91.7% on complete speech and 100% on voiced speech, were achieved in optimal paired subbands.