×

Language Model Selection for Speech-to-Text Conversion

  • US 20110153324A1
  • Filed: 12/22/2010
  • Published: 06/23/2011
  • Est. Priority Date: 12/23/2009
  • Status: Active Grant
First Claim
Patent Images

1. A method of converting speech to text, comprising:

  • receiving at a computer server system from an electronic device sound information from a user of the electronic device, and a context identifier that indicates a context within which the user provided the sound information;

    using the context identifier to select, from among a plurality of language models, a language model appropriate for the context;

    converting speech in the sound information to text using the selected language model; and

    providing the text for use by the electronic device.

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