×

SYSTEM AND METHOD FOR DISTRIBUTED TEXT-TO-SPEECH SYNTHESIS AND INTELLIGIBILITY

  • US 20100268539A1
  • Filed: 04/21/2009
  • Published: 10/21/2010
  • Est. Priority Date: 04/21/2009
  • Status: Active Grant
First Claim
Patent Images

1. A method for creating an audio index representation of an audio file from text input in a form of a text string and producing the audio file from the audio index representation, the method comprising:

  • receiving the text string;

    converting the text string to an audio index representation of an audio file associated with the text string at a text-to-speech synthesizer, the converting including selecting at least one audio unit from a first audio unit synthesis inventory having a plurality of audio units, the selected at least one audio unit forming the audio file;

    representing the selected at least one audio unit with the audio index representation; and

    reproducing the audio file by concatenating the audio units identified in the audio index representation from the first audio unit inventory or a second audio unit synthesis inventory having the audio units identified in the audio index representation.

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