ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

Channel identification and spectrum estimation for robust automatic speech recognition

Yunxin Zhao

A feature estimation technique is proposed for speech signals that are corrupted by both additive and convolutive noises via com-bining channel identification with power spectrum estimation. A correlation-matching algorithm is developed for channel identification, and a Gaussian mixture density model of speech DFT spectra is formulated for estimation of speech power spectra. Cepstral features of speech are calculated from the estimated power spec-tra. Using the proposed method, significantly improved accuracy was achieved on speaker-independent continuous speech recognition where the speech data were corrupted by a simulated linear distortion channel and additive white noise.


Cite as: Zhao, Y. (1999) Channel identification and spectrum estimation for robust automatic speech recognition. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2877-2880

@inproceedings{zhao99b_eurospeech,
  author={Yunxin Zhao},
  title={{Channel identification and spectrum estimation for robust automatic speech recognition}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={2877--2880}
}