P.McCourt, S.Vaseghi, N.Harte ‘Multi-resolution cepstral features for phoneme recognition across speech sub-bands’ in proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Seattle, USA, 12-15 May 1998, 1, IEEE, pp 557-560
Multi-resolution sub-band cepstral features strive to exploit
discriminative cues in localised regions of the spectral domain
by supplementing the full bandwith cepstral features with subband
cepstral features derived from several levels of sub-band
decomposition. Mult-iresolution feature vectors, formed by
concatenation of the subband cepstral features into an extended
feature vector, are shown to yield better performance than
conventional MFCCs for phoneme recognition on the TIMIT
database. Possible strategies for the recombination of partial
recognition scores from independent multi-resoltuion sub-band
models are explored. By exploiting the sub-band variations in
signal to noise ratio for linearly weighted recombination of the
log likelihood probabilities we obtained improved phoneme
recognition performance in broadband noise compared to MFCC
features. This is an advantage over a purely sub-band approach
using non linear recombination which is robust only to narrow
Please note: There is a known bug in some browsers that causes an
error when a user tries to view large pdf file within the browser window.
If you receive the message "The file is damaged and could not be
repaired", please try one of the solutions linked below based on the
browser you are using.
Items in TARA are protected by copyright, with all rights reserved, unless otherwise indicated.