Patents by Inventor Steven A. Wegmann

Steven A. Wegmann 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).

  • Publication number: 20180174585
    Abstract: An interaction assistant conducts multiple turn interaction dialogs with a user in which context is maintained between turns, and the system manages the dialog to achieve an inferred goal for the user. The system includes a linguistic interface to a user and a parser for processing linguistic events from the user. A dialog manager of the system is configured to receive alternative outputs from the parser, and selecting an action and causing the action to be performed based on the received alternative outputs. The system further includes a dialog state for an interaction with the user, and the alternative outputs represent alternative transitions from a current dialog state to a next dialog state. The system further includes a storage for a plurality of templates, and wherein each dialog state is defined in terms of an interrelationship of one or more instances of the templates.
    Type: Application
    Filed: February 14, 2018
    Publication date: June 21, 2018
    Inventors: Jacob Andreas, Taylor D. Berg-Kirkpatrick, Pengyu Chen, Jordan R. Cohen, Laurence S. Gillick, David Leo Wright Hall, Daniel Klein, Michael Newman, Adam D. Pauls, Daniel L. Roth, Jesse Daniel Eskes Rusak, Andrew R. Volpe, Steven A. Wegmann
  • Publication number: 20180114522
    Abstract: A system eliminates alignment processing and performs TTS functionality using a new neural architecture. The neural architecture includes an encoder and a decoder. The encoder receives an input and encodes it into vectors. The encoder applies a sequence of transformations to the input and generates a vector representing the entire sentence. The decoder takes the encoding and outputs an audio file, which can include compressed audio frames.
    Type: Application
    Filed: October 24, 2017
    Publication date: April 26, 2018
    Applicant: Semantic Machines, Inc.
    Inventors: David Leo Wright Hall, Daniel Klein, Daniel Roth, Lawrence Gillick, Andrew Maas, Steven Wegmann
  • Publication number: 20170140755
    Abstract: An interaction assistant conducts multiple turn interaction dialogs with a user in which context is maintained between turns, and the system manages the dialog to achieve an inferred goal for the user. The system includes a linguistic interface to a user and a parser for processing linguistic events from the user. A dialog manager of the system is configured to receive alternative outputs from the parser, and selecting an action and causing the action to be performed based on the received alternative outputs. The system further includes a dialog state for an interaction with the user, and the alternative outputs represent alternative transitions from a current dialog state to a next dialog state. The system further includes a storage for a plurality of templates, and wherein each dialog state is defined in terms of an interrelationship of one or more instances of the templates.
    Type: Application
    Filed: November 10, 2016
    Publication date: May 18, 2017
    Inventors: Jacob Andreas, Taylor D. Being-Kirkpatrick, Pengyu Chen, Jordan R. Cohen, Laurence S Gillsick, David Leo Wright Hall, Daniel Klein, Michael Newman, Adam D. Pauls, Daniel L. Roth, Jesse Daniel Eskes Rusak, Andrew R. Volpe, Steven A. Wegmann
  • Patent number: 8065144
    Abstract: A method for speech recognition. The method uses a single pronunciation estimator to train acoustic phoneme models and recognize utterances from multiple languages. The method includes accepting text spellings of training words in a plurality of sets of training words, each set corresponding to a different one of a plurality of languages. The method also includes, for each of the sets of training words in the plurality, receiving pronunciations for the training words in the set, the pronunciations being characteristic of native speakers of the language of the set, the pronunciations also being in terms of subword units at least some of which are common to two or more of the languages. The method also includes training a single pronunciation estimator using data comprising the text spellings and the pronunciations of the training words.
    Type: Grant
    Filed: February 3, 2010
    Date of Patent: November 22, 2011
    Assignee: Voice Signal Technologies, Inc.
    Inventors: Laurence S. Gillick, Thomas E. Lynch, Michael J. Newman, Daniel L. Roth, Steven A. Wegmann, Jonathan P. Yamron
  • Patent number: 7716050
    Abstract: A method for speech recognition. The method uses a single pronunciation estimator to train acoustic phoneme models and recognize utterances from multiple languages. The method includes accepting text spellings of training words in a plurality of sets of training words, each set corresponding to a different one of a plurality of languages. The method also includes, for each of the sets of training words in the plurality, receiving pronunciations for the training words in the set, the pronunciations being characteristic of native speakers of the language of the set, the pronunciations also being in terms of subword units at least some of which are common to two or more of the languages. The method also includes training a single pronunciation estimator using data comprising the text spellings and the pronunciations of the training words.
    Type: Grant
    Filed: November 17, 2003
    Date of Patent: May 11, 2010
    Assignee: Voice Signal Technologies, Inc.
    Inventors: Laurence S. Gillick, Thomas E. Lynch, Michael J. Newman, Daniel L. Roth, Steven A. Wegmann, Jonathan P. Yamron
  • Patent number: 7467087
    Abstract: The error rate of a pronunciation guesser that guesses the phonetic spelling of words used in speech recognition is improved by causing its training to weigh letter-to-phoneme mappings used as data in such training as a function of the frequency of the words in which such mappings occur. Preferably the ratio of the weight to word frequency increases as word frequencies decreases. Acoustic phoneme models for use in speech recognition with phonetic spellings generated by a pronunciation guesser that makes errors are trained against word models whose phonetic spellings have been generated by a pronunciation guesser that makes similar errors. As a result, the acoustic models represent blends of phoneme sounds that reflect the spelling errors made by the pronunciation guessers. Speech recognition enabled systems are made by storing in them both a pronunciation guesser and a corresponding set of such blended acoustic models.
    Type: Grant
    Filed: October 10, 2003
    Date of Patent: December 16, 2008
    Inventors: Laurence S. Gillick, Steven A. Wegmann, Jonathan P. Yamron
  • Publication number: 20040210438
    Abstract: A method for speech recognition. The method uses a single pronunciation estimator to train acoustic phoneme models and recognize utterances from multiple languages. The method includes accepting text spellings of training words in a plurality of sets of training words, each set corresponding to a different one of a plurality of languages. The method also includes, for each of the sets of training words in the plurality, receiving pronunciations for the training words in the set, the pronunciations being characteristic of native speakers of the language of the set, the pronunciations also being in terms of subword units at least some of which are common to two or more of the languages. The method also includes training a single pronunciation estimator using data comprising the text spellings and the pronunciations of the training words.
    Type: Application
    Filed: November 17, 2003
    Publication date: October 21, 2004
    Inventors: Laurence S. Gillick, Thomas E. Lynch, Michael J. Newman, Daniel L. Roth, Steven A. Wegmann, Jonathan P. Yamron
  • Patent number: 6224636
    Abstract: The content of a speech sample is recognized using a computer system by evaluating the speech sample against a nonparametric set of training observations, for example, utterances from one or more human speakers. The content of the speech sample is recognized based on the evaluation results. The speech recognition process also may rely on a comparison between the speech sample and a parametric model of the training observations.
    Type: Grant
    Filed: February 28, 1997
    Date of Patent: May 1, 2001
    Assignee: Dragon Systems, Inc.
    Inventors: Steven A. Wegmann, Laurence S. Gillick