Ïkizge Dilimi Kullanarak Metinden Baǧimsiz Konuşmaci Belirlemenin Gürbüzleştirilmesi

In this paper, we propose to use a bispectrum slice for the mel-frequency cepstrum coefficients as robust features, to be used in Gaussian mixture model for text-independent speaker identification. In theory, higher order statistics can suppress additive Gaussian noise and save phase information unlike autocorrelation based (power spectral) methods. Feature extraction is achieved through the mel-frequency filter banks, the cosine transform and the logarithm operation to obtain cepstral coefficients. Performance of our proposed features are then compared with the classical mel-frequency cepstrum coefficients under various noisy test uttarances.