Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
EFFICIENT ADAPTATION TEXT DESIGN BASED ON THE KULLBACK-LEIBLER Xiaodong Cui and Abeer Alwan
 

Summary: EFFICIENT ADAPTATION TEXT DESIGN BASED ON THE KULLBACK-LEIBLER
MEASURE
Xiaodong Cui and Abeer Alwan
Department of Electrical Engineering
University of California, Los Angeles, CA 90095
Email: xdcui@icsl.ucla.edu, alwan@icsl.ucla.edu
ABSTRACT
This paper proposes an efficient algorithm for the automatic
selection of sentences given a desired phoneme distribution.
The algorithm is based on the Kullback-Leibler measure un-
der the criterion of minimum cross-entropy. One applica-
tion of this algorithm is the design of adaptation text for au-
tomatic speech recognition with a particular phoneme dis-
tribution. The algorithm is efficient and flexible, especially
in the case of limited text size. Experimental results verify
the advantage of this approach.
1. INTRODUCTION
The automatic selection of sentences is important in several
applications such as designing speaker adaptation text for
ASR and speech synthesis. In speaker adaptation, the adap-

  

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

 

Collections: Computer Technologies and Information Sciences