Robust text-independent speaker identification using bispectrum slice


Ozkurt T., Akgul T.

IEEE 12th Signal Processing and Communications Applications Conference, Kusadasi, Türkiye, 28 - 30 Nisan 2004, ss.418-421 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/siu.2004.1338552
  • Basıldığı Şehir: Kusadasi
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.418-421
  • İstanbul Teknik Üniversitesi Adresli: Hayır

Özet

In this paper, we propose to use a bispectrurn slice for the mel-frequency cepstrurn 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.