Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Proceedings NIPS5 ContextDependent Multiple Distribution Phonetic Modeling with MLP
 

Summary: Proceedings NIPS5
s
Context­Dependent Multiple Distribution Phonetic Modeling with MLP
Michael Cohen*, Horacio Franco*, Nelson Morgan**,
*
David Rumelhart***, and Victor Abrash*
Speech Research Program, SRI International, Menlo Park, CA 94025
4
** Intl. Computer Science Inst., 1947 Center Street, Suite 600, Berkeley, CA 9470
*** Stanford University, Dept. of Psychology, Stanford, CA 94305
A
Abstract
number of hybrid multilayer perceptron (MLP)/hidden Markov
n
r
model (HMM) speech recognition systems have been developed i
ecent years (Morgan and Bourlard, 1990). In this paper, we present
m
a new MLP architecture and training algorithm which allows the
odeling of context­dependent phonetic classes in a hybrid

  

Source: Abrash, Victor - Speech Technology & Research Laboratory, SRI International

 

Collections: Computer Technologies and Information Sciences