Patents by Inventor Lawrence Kevin Saul

Lawrence Kevin Saul has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Automatic speech recognition using segmented curves of individual speech components having arc lengths generated along space-time trajectories
    Patent number: 6401064
    Abstract: A method and apparatus for speech recognition using Markov processes on curves are presented. The method and apparatus operate such that input speech utterances are received and represented as multidimensional curves. The curve is split into acoustic segments representing different components based on initial model estimates. The segments are used to create a new statistical model for the curve. The process may be reiterated to produce a more precise statistical model for recognition. As a result, feature vectors are extracted from input speech and contribute to a recognition score in proportion to their arc length. The arc lengths are weighted to minimize recognition errors due to variations in speaking rate. In addition, more importance is attached to short-lived but non-stationary sounds, such as consonants.
    Type: Grant
    Filed: May 24, 2001
    Date of Patent: June 4, 2002
    Assignee: AT&T Corp.
    Inventor: Lawrence Kevin Saul
  • Automatic speech recognition using multi-dimensional curve-linear representations
    Patent number: 6301561
    Abstract: A method and apparatus for speech recognition using Markov processes on curves are presented. The method and apparatus operate such that input speech utterances are received and represented as multidimensional curves. The curve is split into acoustic segments representing different components based on initial model estimates. The segments are used to create a new statistical model for the curve. The process may be reiterated to produce a more precise statistical model for recognition. As a result, feature vectors are extracted from input speech and contribute to a recognition score in proportion to their arc length. The arc lengths are weighted to minimize recognition errors due to variations in speaking rate. In addition, more importance is attached to short-lived but non-stationary sounds, such as consonants.
    Type: Grant
    Filed: September 18, 2000
    Date of Patent: October 9, 2001
    Assignee: AT&T Corporation
    Inventor: Lawrence Kevin Saul
  • Method and apparatus for automatic speech recognition using Markov processes on curves
    Patent number: 6148284
    Abstract: A method and apparatus for speech recognition using Markov processes on curves are presented. The method and apparatus operate such that input speech utterances are received and represented as multidimensional curves. The curve is split into acoustic segments representing different components based on initial model estimates. The segments are used to create a new statistical model for the curve. The process may be reiterated to produce a more precise statistical model for recognition. As a result, feature vectors are extracted from input speech and contribute to a recognition score in proportion to their arc length. The arc lengths are weighted to minimize recognition errors due to variations in speaking rate. In addition, more importance is attached to short-lived but non-stationary sounds, such as consonants.
    Type: Grant
    Filed: December 11, 1998
    Date of Patent: November 14, 2000
    Assignee: AT&T Corporation
    Inventor: Lawrence Kevin Saul