×

Biasing voice correction suggestions

  • US 10,679,609 B2
  • Filed: 12/03/2019
  • Issued: 06/09/2020
  • Est. Priority Date: 01/05/2016
  • Status: Active Grant
First Claim
Patent Images

1. A method comprising:

  • receiving, at a user device, a voice input from a user of the user device;

    displaying, by the user device, an initial recognition output in a graphical user interface based on the voice input, the initial recognition output comprising an initial transcription of the voice input, the initial transcription comprising a misrecognized term;

    receiving, at the user device, a selection indication indicating a user selection in the graphical user interface of a portion of the initial recognition output to correct the misrecognized term;

    after receiving the selection indication, displaying, by the user device, a first list of suggested recognition outputs of the voice input in the graphical user interface, each suggested recognition output of the first list comprising a respective phonetic similarity to the received voice input;

    after displaying the first list of suggested recognition outputs, receiving, at the user device, one or more text characters inputted by the user through the graphical user interface; and

    replacing, by the user device, the misrecognized term based on the received one or more text characters to provide a corrected transcription of the voice input.

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