×

Speech recognition system, training arrangement and method of calculating iteration values for free parameters of a maximum-entropy speech model

  • US 7,010,486 B2
  • Filed: 02/13/2002
  • Issued: 03/07/2006
  • Est. Priority Date: 02/13/2001
  • Status: Active Grant
First Claim
Patent Images

1. A method of calculating iteration values for free parameters λ

  • α

    ortho(n) of a maximum-entropy speech model MESM in a speech recognition system with the aid of the generalized iterative scaling training algorithm, the method comprising the step ofiteratively determining;


    λ

    α

    ortho(n+1)=G

    α

    ortho(n), mα

    ortho, . . . ) 

    where;

    n;

    is an iteration parameter;

    G;

    is a mathematical function;

    α

    ;

    is an attribute in the MESM; and

    mα

    ortho;

    is a desired orthogonalized boundary value in the MESM for the attribute α

    ,characterized in that the desired orthogonalized boundary value mα

    ortho is calculated by linearly combining the desired boundary value mα

    with desired boundary values mβ

    of attributes β

    that have a larger range than the attribute α

    .

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×