Patent · US Active

Method for processing the output of a speech recognizer

US8219407B1 · kind B1 · utility

456Cited by
117References
24Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 30, 2008
Grant dateJul 10, 2012
Priority date
Expiry dateMay 11, 2031

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04L2012/2847
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A system and method for processing speech input comprising a speech recognizer and a logical command processor which facilitates additional processing of speech input beyond the speech recognizer level. A speech recognizer receives input from a user, and when a command is identified in the speech input, if the command meets conditions that require additional processing, a representation of the speech input s stored for subsequent processing. A logical command processor performs additional processing of command input by analyzing the command and its elements, determining which elements are required for successful processing the command and which elements are present and lacking. The user is prompted to supply missing information, and subsequent user input is added to the command structure until the command input is aborted or the command structure reaches sufficient completeness to enable execution of the command. Thereby, speech input of complex commands in natural language in a system running a plurality of applications and processes is made possible.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.