×

Speech recognition system trained with regional speech characteristics

DC
  • US 7,225,125 B2
  • Filed: 01/07/2005
  • Issued: 05/29/2007
  • Est. Priority Date: 11/12/1999
  • Status: Expired due to Term
First Claim
Patent Images

1. A method of optimizing recognition of a speech utterance from a user with a distributed speech processing system comprising the steps of:

  • (a) training one or more speech recognition models for recognizing speech utterances in a first natural language in a first training operation;

    wherein said speech recognition models are implemented as part of a speech recognition engine executing on a network server system of the distributed speech processing system;

    wherein said first training operation is based on samples of speech from a group of persons employing said first natural language and which are communicated over a network to the distributed speech processing system from geographic regions served by the distributed speech processing system, such that said speech recognition models are derived and constituted at least in part at said network server system;

    wherein recognition of speech utterances during a speech recognition process is optimized for a geographic region by using one or more speech models which include variants of words to be uttered by users of the distributed speech processing system;

    (b) configuring a set of speech recognition operations to be performed by the network server system based on computing resources available to such system.

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