×

Apparatus and methods using a pattern matching speech recognition engine to train a natural language speech recognition engine

  • US 9,767,793 B2
  • Filed: 06/08/2012
  • Issued: 09/19/2017
  • Est. Priority Date: 06/08/2012
  • Status: Active Grant
First Claim
Patent Images

1. A method performed on at least one processor for training a user profile for a continuous speech recognition engine, the method comprising the steps of:

  • providing an audio file wherein the audio file contains a pronunciation of a client;

    recognizing the audio file as text data using a first speech recognition engine, wherein the first speech recognition engine is not a continuous speech recognition engine;

    linking the audio file and the text data generated by the first speech recognition engine;

    initially training a user profile of a second speech recognition engine, which is the continuous speech recognition engine, using the linked audio file and text data, wherein the user profile of the continuous speech recognition engine is initially trained using the linked audio and text data recognized by the first speech recognition engine and wherein only the first speech recognition engine recognizes audio until the user profile is at least initially trained and wherein the second speech recognition engine only recognizes audio after at least a portion of the initial training of the user profile is completed such that until at least the portion of the initial training of the user profile is complete only the first speech recognition engine recognizes audio.

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