Patents by Inventor Peter Vincent de Souza

Peter Vincent de Souza 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).

  • Determining and using acoustic confusability, acoustic perplexity and synthetic acoustic word error rate
    Patent number: 7219056
    Abstract: Two statistics are disclosed for determining the quality of language models. These statistics are called acoustic perplexity and the synthetic acoustic word error rate (SAWER), and they depend upon methods for computing the acoustic confusability of words. It is possible to substitute models of acoustic data in place of real acoustic data in order to determine acoustic confusability. An evaluation model is created, a synthesizer model is created, and a matrix is determined from the evaluation and synthesizer models. Each of the evaluation and synthesizer models is a hidden Markov model. Once the matrix is determined, a confusability calculation may be performed. Different methods are used to determine synthetic likelihoods. The confusability may be normalized and smoothed and methods are disclosed that increase the speed of performing the matrix inversion and the confusability calculation. A method for caching and reusing computations for similar words is disclosed.
    Type: Grant
    Filed: April 19, 2001
    Date of Patent: May 15, 2007
    Assignee: International Business Machines Corporation
    Inventors: Scott Elliot Axelrod, Peder Andreas Olsen, Harry William Printz, Peter Vincent de Souza
  • Determining and using acoustic confusability, acoustic perplexity and synthetic acoustic word error rate
    Publication number: 20020032549
    Abstract: Two statistics are disclosed for determining the quality of language models. These statistics are called acoustic perplexity and the synthetic acoustic word error rate (SAWER), and they depend upon methods for computing the acoustic confusability of words. It is possible to substitute models of acoustic data in place of real acoustic data in order to determine acoustic confusability. An evaluation model is created, a synthesizer model is created, and a matrix is determined from the evaluation and synthesizer models. Each of the evaluation and synthesizer models is a hidden Markov model. Once the matrix is determined, a confusability calculation may be performed. Different methods are used to determine synthetic likelihoods. The confusability may be normalized and smoothed and methods are disclosed that increase the speed of performing the matrix inversion and the confusability calculation. A method for caching and reusing computations for similar words is disclosed.
    Type: Application
    Filed: April 19, 2001
    Publication date: March 14, 2002
    Applicant: International Business Machines Corporation
    Inventors: Scott Elliot Axelrod, Peder Andreas Olsen, Harry William Printz, Peter Vincent de Souza
  • Method and apparatus for constructing continuous parameter fenonic hidden markov models by replacing phonetic models with continous fenonic models
    Patent number: 5737490
    Abstract: A method and apparatus for constructing a hidden Markov model comprised of multiple fenones characterized by their duration and a set of acoustic properties. The present invention provides a sequence of fenones to model a speech event. The sequence may undergo modifications to improve the overall performance of the model.
    Type: Grant
    Filed: October 22, 1996
    Date of Patent: April 7, 1998
    Assignee: Apple Computer, Inc.
    Inventors: Stephen Christopher Austin, Peter Vincent de Souza