×

INTERACTIVE DEBUGGING AND TUNING OF METHODS FOR CTTS VOICE BUILDING

  • US 20090083037A1
  • Filed: 12/03/2008
  • Published: 03/26/2009
  • Est. Priority Date: 10/17/2003
  • Status: Active Grant
First Claim
Patent Images

1. A system for debugging and tuning synthesized audio, comprising:

  • means for receiving a user-supplied text with a visual user interface;

    means for generating synthesized audio generated from concatenated phonetic units, the synthesized audio being a voice rendering of the user-supplied text;

    means for displaying the waveform corresponding to synthesized audio generated from concatenated phonetic units;

    means for displaying parameters corresponding to at least one of the phonetic units, the parameters including configuration parameters comprising at least one weight for adjusting at least one search cost function, the at least one weight comprising at least one of a pitch cost weight and a duration cost weight;

    means for displaying an original recording containing a selected phonetic unit;

    means for receiving an editing input from the user; and

    means for adjusting the parameters in accordance with the editing input by adjusting and storing in a text-to-speech engine configuration file at least one configuration parameter, wherein adjusting includes repositioning a phonetic alignment marker.means for highlighting in the display of the original recording at least one user-selected phonetic unit;

    means for correcting elements of a text-to-speech segment dataset of parameters corresponding to a segment of the synthesized audio identified as be problematic;

    means for generating a new synthesized waveform corresponding to one or more adjusted parameters; and

    wherein the system continues to regenerate new synthesized waveforms until a desired synthesized output is generated.

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