Sixth International Conference on Spoken Language Processing
October 16-20, 2000
Speaker Feature Extraction from Pitch Information Based on Spectral Subtraction for Speaker Identification
Yoshiroh Itoh, Jun Toyama, Masaru Shimbo
Graduate School of Engineering, Hokkaido University, Japan
Robust speaker feature extraction under noise
conditions is an important issue for application of a
speaker recognition system.
It is well known that LPC cepstrum, which expresses
the spectral envelope, is eective for speaker recognition.
This implies that the spectral rough structure is
eective for speaker recognition. However, LPC
cepstrum is a noise-sensitive feature.
On the other hand, spectral subtraction is an
effective speech enhancement method under stationary
In this study, we developed a new method for
feature extraction based on spectral subtraction and noise
robust spectral rough structures, and we evaluated
the eectiveness of the feature extraction method in
speaker identification experiments.
Itoh, Yoshiroh / Toyama, Jun / Shimbo, Masaru (2000):
"Speaker feature extraction from pitch information based on spectral subtraction for speaker identification",
In ICSLP-2000, vol.2, 310-313.