Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
MULTI-PARAMETER FREQUENCY WARPING FOR VTLN BY GRADIENT SEARCH Sankaran Panchapagesan and Abeer Alwan
 

Summary: MULTI-PARAMETER FREQUENCY WARPING FOR VTLN BY GRADIENT SEARCH
Sankaran Panchapagesan and Abeer Alwan
Department of Electrical Engineering
University of California, Los Angeles, U.S.A.
panchap, abeera @ icsl.ucla.edu
ABSTRACT
The current method for estimating frequency warping (FW) func-
tions for vocal tract length normalization (VTLN) is by maximizing
the ASR likelihood score by an exhaustive search over a grid of FW
parameters. Exhaustive search is inefficient when estimating multi-
parameter FWs, which have been shown to give improvements in
recognition accuracy over single parameter FWs [8]. Here we de-
velop a gradient search algorithm to obtain the optimal FW parame-
ters for MFCC features, since previous work focussed on PLP cep-
stral features [8]. The novel calculation involved was that of the gra-
dient of the Mel filterbank with respect to the FW parameters. Even
for a single parameter, the gradient search method was more efficient
than grid search by a factor of around 1.6 on the average for male
children speakers tested on models trained from adult males. When
used to estimate multi-parameter sine-log allpass transform (SLAPT,

  

Source: Alwan, Abeer - Electrical Engineering Department, University of California at Los Angeles

 

Collections: Computer Technologies and Information Sciences