Third-Order moments of filtered speech signals for robust speech recognition

Authors:
Kevin M. Indrebo;Richard J. Povinelli;Michael T. Johnson
Affiliations:
Dept. of Electrical and Computer Engineering, Marquette University, Milwaukee, Wisconsin;Dept. of Electrical and Computer Engineering, Marquette University, Milwaukee, Wisconsin;Dept. of Electrical and Computer Engineering, Marquette University, Milwaukee, Wisconsin
Venue:
NOLISP'05 Proceedings of the 3rd international conference on Non-Linear Analyses and Algorithms for Speech Processing
Year:
2005

Citing 1
Cited 2

Speech and Audio Signal Processing: Processing and Perception of Speech and Music

Speech and Audio Signal Processing: Processing and Perception of Speech and Music

Unbiased adaptive estimations of the fourth-order cumulant for real random zero-mean signal

IEEE Transactions on Signal Processing
Combining Mel frequency Cepstral coefficients and fractal dimensions for automatic speech recognition

NOLISP'11 Proceedings of the 5th international conference on Advances in nonlinear speech processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Novel speech features calculated from third-order statistics of subband-filtered speech signals are introduced and studied for robust speech recognition. These features have the potential to capture nonlinear information not represented by cepstral coefficients. Also, because the features presented in this paper are based on the third-order moments, they may be more immune to Gaussian noise than cepstrals, as Gaussian distributions have zero third-order moments. Experiments on the AURORA2 database studying these features in combination with Mel-frequency cepstral coefficients (MFCC's) are presented, and some improvement over the MFCC-only baseline is shown when clean speech is used for training, though the same improvement is not seen when multi-condition training data is used.