×

Techniques for disambiguating speech input using multimodal interfaces

  • US 20040172258A1
  • Filed: 12/10/2003
  • Published: 09/02/2004
  • Est. Priority Date: 12/10/2002
  • Status: Active Grant
First Claim
Patent Images

1. A system for disambiguating speech input comprising:

  • a speech recognition component that receives recorded audio or speech input and generates;

    one or more tokens corresponding to the speech input; and

    for each of the one or more tokens, a confidence value indicative of the likelihood that the a given token correctly represents the speech input;

    a selection component that identifies, according to a selection algorithm, which two or more tokens are to be presented to a user as alternatives;

    one or more disambiguation components that perform an interaction with the user to present the alternatives and to receive a selection of alternatives from the user, the interaction taking place in at least a visual mode; and

    an output interface that presents the selected alternative to an application as input.

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