Discrimination of severely noisy pathological voice with spectral slope and HNR

@article{Li2004DiscriminationOS,
  title={Discrimination of severely noisy pathological voice with spectral slope and HNR},
  author={Tao Li and Cheolwoo Jo},
  journal={Proceedings 7th International Conference on Signal Processing, 2004. Proceedings. ICSP '04. 2004.},
  year={2004},
  volume={3},
  pages={2218-2221 vol.3}
}
In this paper we tried to discriminate severely noisy pathological voice from normal ones based on two different parameters, spectral slope and ratio of energies in harmonic and noise components (HNR). The spectral slope was obtained by using a curve filling method and the HNR was computed from cepstrum. Speech data from normal peoples and patients were collected, then diagnosed and classified into three different categories (normal, relatively less noisy and severely noisy data). The mean and… CONTINUE READING