ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Noise robust speech recognition using a dynamic-cepstrum

Kiyoaki Aikawa, Tsuyoshi Saito

Noise robust speech recognition is achieved using a dynamic-cepstrum. The dynamic-cepstrum is a new spectral representation incorporating time-frequency forward masking. The time-frequency masking can suppress the spectral components commonly included in the current spectrum and in the preceding spectra. This feature suggests the applicability of the dynamic-cepstrum to noisy speech recognition. Speaker-dependent and speaker-independent phoneme recognition experiments are conducted using hidden Markov models. Experimental results demonstrate that the dynamic-cepstrum outperforms the conventional cepstrum on robustness against stationary noise and amplitude-modulated noise. The dynamic-cepstrum is also found to be superior to the conventional cepstrum combined with a delta-cepstrum.


Cite as: Aikawa, K., Saito, T. (1994) Noise robust speech recognition using a dynamic-cepstrum. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 1579-1582

@inproceedings{aikawa94_icslp,
  author={Kiyoaki Aikawa and Tsuyoshi Saito},
  title={{Noise robust speech recognition using a dynamic-cepstrum}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={1579--1582}
}