×

AUTOMATED VOICE AND SPEECH LABELING

  • US 20130262111A1
  • Filed: 03/14/2013
  • Published: 10/03/2013
  • Est. Priority Date: 03/30/2012
  • Status: Active Grant
First Claim
Patent Images

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

  • receiving a digital signal comprising a recorded spoken input;

    obtaining at least one measurement of said digital signal;

    identifying at least one characteristic of said digital signal by comparing said at least one measurement of said digital signal to a database of digital audio signal characteristics;

    transcribing at least a portion of said recorded spoken input using said at least one characteristic of said digital signal to create an initial transcription;

    calculating at least one speech sound phonetic identification value;

    transcribing at least a second portion of said recorded spoken input using said first transcription and said at least one speech sound phonetic identification value.

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