TITLE

Learning Tract Variables with Distal Supervised Learning Model

AUTHOR(S)
Ying Chen; Shaobai Zhang
PUB. DATE
February 2013
SOURCE
Journal of Networks;Feb2013, Vol. 8 Issue 2, p397
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
This paper compared the performance of tract variables (TVs) estimation with pellet trajectory estimation by using the trajectory mixture density networks (TMDN), and the result indicated that TVs can be estimated more accurately than the pellet trajectories. We used eight tract variables as articulatory information to model speech dynamics, and parameterized the speech signal as melfrequency cepstral coefficients (MFCCs) and acoustic parameters (APs), and then we analyzed TV estimation using the distal supervised learning (DSL) model. For the DSL, we first analyzed its theoretical foundation and then proposed a global optimization approach for its inversion model. The results of the experiment showed that distal supervised learning has a good estimation performance for tract variables, so it plays an important role in speech inversion and gesture-based ASR architecture.
ACCESSION #
86708157

 

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics