ETRW on Speech Processing in Adverse Conditions Cannes-Mandelieu, France November 10-13, 1992

Robust Signal Preprocessing for Word Recognition in Noisy Environment

H. Eckhardt, M. Trompf, G. Angleys, Heidi Hackbarth

ALCATEL SEL, Dept. ZFZ/SC3, Stuttgart, Germany

Reliable word recognition from degraded speech signals requires the incorporation of robust feature extraction as well as noise reduction into the system. This paper is focused on the comparison of different feature extraction methods with respect to different types of distortions. The experiments were made to tackle the problems of additive and convolutional noise as well as with the speaker-stress related Lombard effect, and are part of our ongoing work in the area of robust speech recognition.

Full Paper

Bibliographic reference.  Eckhardt, H. / Trompf, M. / Angleys, G. / Hackbarth, Heidi (1992): "Robust signal preprocessing for word recognition in noisy environment", In SPAC-1992, 85-88.