×

Training And Applying Prosody Models

  • US 20100042410A1
  • Filed: 08/11/2009
  • Published: 02/18/2010
  • Est. Priority Date: 08/12/2008
  • Status: Active Grant
First Claim
Patent Images

1. A computer-implementable method for synthesizing audible speech, with varying prosody, from textual content, the method comprising:

  • generating a first text annotated with prosody information using a speech recognition engine;

    training a prosody model with the first text annotated with prosody information;

    applying the prosody model to textual content to produce a second text annotated with prosody information; and

    synthesizing audible speech from the second text annotated with prosody information.

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