8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Improved Feature Extraction Based on Spectral Noise Reduction and Nonlinear Feature Normalization

Jose C. Segura, Javier Ramirez, Carmen Benitez, Angel de la Torre, Antonio J. Rubio

Universidad de Granada, Spain

This paper is mainly focused on showing experimental results of a feature extraction algorithm that combines spectral noise reduction and nonlinear feature normalization. The successfulness of this approach has been shown in a previous work, and in this one, we present several improvements that result in a performance comparable to that of the recently approved AFE for DSR. Noise reduction is now based on a Wiener filter instead of spectral subtraction. The voice activity detection based on the full-band energy has been replaced with a new one using spectral information. Relative improvements of 24.81% and 17.50% over our previous system are obtained for AURORA 2 and 3 respectively. Results for AURORA 2 are not as good as those for the AFE, but for AURORA 3 a relative improvement of 5.27% is obtained.

Full Paper

Bibliographic reference.  Segura, Jose C. / Ramirez, Javier / Benitez, Carmen / Torre, Angel de la / Rubio, Antonio J. (2003): "Improved feature extraction based on spectral noise reduction and nonlinear feature normalization", In EUROSPEECH-2003, 353-356.