×

Method for processing the output of a speech recognizer

  • US 9,753,912 B1
  • Filed: 10/23/2015
  • Issued: 09/05/2017
  • Est. Priority Date: 12/27/2007
  • Status: Active Grant
First Claim
Patent Images

1. A method for processing speech, comprising:

  • receiving information representing speech input;

    parsing the received information representing speech input with respect to a plurality of predetermined command contexts, the plurality of predetermined command contexts comprising command contexts of a plurality of different applications, in an automated speech information processing system;

    determining, with at least one automated processor;

    if the parsed received information representing speech input corresponds to a command of a respective predetermined command context for execution of the command, and based on the determination that the parsed received information representing speech input corresponds to a command of the respective predetermined command context for reliable execution, then executing the command by a respective application associated with the respective predetermined command context;

    if the parsed received information representing speech input cannot be executed, and based on the determination that the parsed received information representing speech input cannot be executed, then prompting for further information representing speech input, to reduce ambiguity or increase completeness, in dependence on previously received information representing speech input and the plurality of predetermined command contexts; and

    if an abort, fail or cancel condition is detected in further information representing speech input, and based on the determination that the abort, fail or cancel condition is detected in the further information representing speech input, then exiting said determining.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×