Cepstral domain feature compensation based on diagonal approximation

Woohyung Lim, Chang Woo Han, Jong Won Shin, Nam Soo Kim

Abstract

In this paper, we propose a novel approach to feature compensation performed in the cepstral domain. We apply the linear approximation method in the cepstral domain to simplify the relationship among clean speech, noise and noisy speech. Conventional log-spectral domain feature compensation methods usually assume that each log-spectral coefficient is independent, which is far from real observations. Processing in the cepstral domain has the advantage that the spectral correlation among different frequencies are taken into consideration. By using the diagonal covariance approximation, we can easily modify the conventional log-spectral domain feature compensation technique to fit to the cepstral domain. The proposed approach shows significant improvements in the AURORA2 speech recognition task.
BibTeX
@inproceedings{lim2008cepstral,
  author = {Woohyung Lim and Chang Woo Han and Jong Won Shin and Nam Soo Kim},
  title = {{Cepstral domain feature compensation based on diagonal approximation}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2008},
  doi = {10.1109/icassp.2008.4518631},
}

Loading related content...

Figure