×

Speech based learning/training system using semantic decoding

DC
  • US 7,392,185 B2
  • Filed: 06/25/2003
  • Issued: 06/24/2008
  • Est. Priority Date: 11/12/1999
  • Status: Expired due to Fees
First Claim
Patent Images

1. A method of populating a natural language speech lattice with semantically variant questions, the method comprising the steps of:

  • (a) providing a target set of questions associated with a content of a task domain that is to be supported by the natural language speech lattice;

    (a)′

    receiving a first user question from said target set of questions;

    (b) dividing the user question into a plurality of words corresponding to the user question;

    (c) determining synonyms for selected words in said plurality of words;

    (d) formulating a synonym set of questions related to said user question based on said synonyms;

    (e) performing semantic decoding on said synonym set of questions, to identify a disambiguated set of questions;

    (f) storing said set of disambiguated questions in a speech recognition lattice;

    wherein said set of disambiguated questions correspond to semantic variants of said target set of questions that can be recognized by a natural language speech engine used for the task domain.

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