×

Multimodal speech recognition system

  • US 20080133228A1
  • Filed: 11/30/2007
  • Published: 06/05/2008
  • Est. Priority Date: 11/30/2006
  • Status: Active Grant
First Claim
Patent Images

1. A multimodal system for receiving inputs via more than one mode from a user and for interpretation and display of the text intended by the inputs received through those multiple modes, the system comprising:

  • a) a user input device having a plurality of modes with one mode for accessing speech and each of the remaining modes being associated with an input method for entering letters or characters or words or phrases or sentences or graphics or image or any combination;

    b) a memory containing a plurality of acoustic networks, each of the plurality of acoustic networks associated with one or more inputs from the one or more modes;

    c) a mechanism to feed back the system output to a user of the input device, in the form of a visual display or an audible speaker; and

    d) a processor to;

    i) process the inputs received via the multiple modes and select and/or build an appropriate acoustic network;

    ii) perform automatic speech recognition using the selected/built acoustic network; and

    iii) return the recognition outputs to the user for subsequent user-actions.

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