Patents by Inventor Martin Graciarena

Martin Graciarena 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).

  • Patent number: 11217228
    Abstract: Systems and methods for speech recognition are provided. In some aspects, the method comprises receiving, using an input, an audio signal. The method further comprises splitting the audio signal into auditory test segments. The method further comprises extracting, from each of the auditory test segments, a set of acoustic features. The method further comprises applying the set of acoustic features to a deep neural network to produce a hypothesis for the corresponding auditory test segment. The method further comprises selectively performing one or more of: indirect adaptation of the deep neural network and direct adaptation of the deep neural network.
    Type: Grant
    Filed: March 22, 2017
    Date of Patent: January 4, 2022
    Assignee: SRI International
    Inventors: Vikramjit Mitra, Horacio E. Franco, Chris D. Bartels, Dimitra Vergyri, Julien van Hout, Martin Graciarena
  • Patent number: 11152016
    Abstract: Embodiments of the disclosed technologies include finding content of interest in an RF spectrum by automatically scanning the RF spectrum; detecting, in a range of frequencies of the RF spectrum that includes one or more undefined channels, a candidate RF segment; where the candidate RF segment includes a frequency-bound time segment of electromagnetic energy; executing a machine learning-based process to determine, for the candidate RF segment, signal characterization data indicative of one or more of: a frequency range, a modulation type, a timestamp; using the signal characterization data to determine whether audio contained in the candidate RF segment corresponds to a search criterion; in response to determining that the candidate RF segment corresponds to the search criterion, outputting, through an electronic device, data indicative of the candidate RF segment; where the data indicative of the candidate RF segment is output in a real-time time interval after the candidate RF segment is detected.
    Type: Grant
    Filed: May 8, 2019
    Date of Patent: October 19, 2021
    Assignee: SRI INTERNATIONAL
    Inventors: Aaron D. Lawson, Harry Bratt, Mitchell L. McLaren, Martin Graciarena
  • Publication number: 20200184997
    Abstract: Embodiments of the disclosed technologies include finding content of interest in an RF spectrum by automatically scanning the RF spectrum; detecting, in a range of frequencies of the RF spectrum that includes one or more undefined channels, a candidate RF segment; where the candidate RF segment includes a frequency-bound time segment of electromagnetic energy; executing a machine learning-based process to determine, for the candidate RF segment, signal characterization data indicative of one or more of: a frequency range, a modulation type, a timestamp; using the signal characterization data to determine whether audio contained in the candidate RF segment corresponds to a search criterion; in response to determining that the candidate RF segment corresponds to the search criterion, outputting, through an electronic device, data indicative of the candidate RF segment; where the data indicative of the candidate RF segment is output in a real-time time interval after the candidate RF segment is detected.
    Type: Application
    Filed: May 8, 2019
    Publication date: June 11, 2020
    Inventors: Aaron D. Lawson, Harry Bratt, Mitchell L. McLaren, Martin Graciarena
  • Publication number: 20200168208
    Abstract: Systems and methods for speech recognition are provided. In some aspects, the method comprises receiving, using an input, an audio signal. The method further comprises splitting the audio signal into auditory test segments. The method further comprises extracting, from each of the auditory test segments, a set of acoustic features. The method further comprises applying the set of acoustic features to a deep neural network to produce a hypothesis for the corresponding auditory test segment. The method further comprises selectively performing one or more of: indirect adaptation of the deep neural network and direct adaptation of the deep neural network.
    Type: Application
    Filed: March 22, 2017
    Publication date: May 28, 2020
    Inventors: Vikramjit Mitra, Horacio E. Franco, Chris D. Bartels, Dimitra Vergyri, Julien van Hout, Martin Graciarena
  • Patent number: 10478111
    Abstract: A computer-implemented method can include a speech collection module collecting a speech pattern from a patient, a speech feature computation module computing at least one speech feature from the collected speech pattern, a mental health determination module determining a state-of-mind of the patient based at least in part on the at least one computed speech feature, and an output module providing an indication of a diagnosis with regard to a possibility that the patient is suffering from a certain condition such as depression or Post-Traumatic Stress Disorder (PTSD).
    Type: Grant
    Filed: August 5, 2015
    Date of Patent: November 19, 2019
    Assignee: SRI International
    Inventors: Bruce Knoth, Dimitra Vergyri, Elizabeth Shriberg, Vikramjit Mitra, Mitchell McLaren, Andreas Kathol, Colleen Richey, Martin Graciarena
  • Publication number: 20180214061
    Abstract: A computer-implemented method can include a speech collection module collecting a speech pattern from a patient, a speech feature computation module computing at least one speech feature from the collected speech pattern, a mental health determination module determining a state-of-mind of the patient based at least in part on the at least one computed speech feature, and an output module providing an indication of a diagnosis with regard to a possibility that the patient is suffering from a certain condition such as depression or Post-Traumatic Stress Disorder (PTSD).
    Type: Application
    Filed: August 5, 2015
    Publication date: August 2, 2018
    Inventors: Bruce Knoth, Dimitra Vergyri, Elizabeth Shriberg, Vikramjit Mitra, Mitchell McLaren, Andreas Kathol, Colleen Richey, Martin Graciarena
  • Publication number: 20170061316
    Abstract: The present invention relates to a method and apparatus for tailoring the output of an intelligent automated assistant. One embodiment of a method for conducting an interaction with a human user includes collecting data about the user using a multimodal set of sensors positioned in a vicinity of the user, making a set of inferences about the user in accordance with the data, and tailoring an output to be delivered to the user in accordance with the set of inferences.
    Type: Application
    Filed: November 16, 2016
    Publication date: March 2, 2017
    Inventors: Gokhan Tur, Horacio E. Franco, Elizabeth Shriberg, Gregory K. Myers, William S. Mark, Norman D. Winarsky, Andreas Stolcke, Bart Peintner, Michael J. Wolverton, Luciana Ferrer, Martin Graciarena, Neil Yorke-Smith, Harry Bratt
  • Patent number: 9564134
    Abstract: The present invention relates to a method and apparatus for speaker-calibrated speaker detection. One embodiment of a method for generating a speaker model for use in detecting a speaker of interest includes identifying one or more speech features that best distinguish the speaker of interest from a plurality of impostor speakers and then incorporating the speech features in the speaker model.
    Type: Grant
    Filed: September 28, 2015
    Date of Patent: February 7, 2017
    Assignee: SRI INTERNATIONAL
    Inventors: Elizabeth Shriberg, Luciana Ferrer, Andreas Stolcke, Martin Graciarena, Nicolas Scheffer
  • Patent number: 9501743
    Abstract: The present invention relates to a method and apparatus for tailoring the output of an intelligent automated assistant. One embodiment of a method for conducting an interaction with a human user includes collecting data about the user using a multimodal set of sensors positioned in a vicinity of the user, making a set of inferences about the user in accordance with the data, and tailoring an output to be delivered to the user in accordance with the set of inferences.
    Type: Grant
    Filed: December 2, 2015
    Date of Patent: November 22, 2016
    Assignee: SRI INTERNATIONAL
    Inventors: Gokhan Tur, Horacio E. Franco, Elizabeth Shriberg, Gregory K. Myers, William S. Mark, Norman D. Winarsky, Andreas Stolcke, Bart Peintner, Michael J. Wolverton, Luciana Ferrer, Martin Graciarena, Neil Yorke-Smith, Harry Bratt
  • Publication number: 20160118049
    Abstract: The present invention relates to a method and apparatus for speaker-calibrated speaker detection. One embodiment of a method for generating a speaker model for use in detecting a speaker of interest includes identifying one or more speech features that best distinguish the speaker of interest from a plurality of impostor speakers and then incorporating the speech features in the speaker model.
    Type: Application
    Filed: September 28, 2015
    Publication date: April 28, 2016
    Inventors: Elizabeth Shriberg, Luciana Ferrer, Andreas Stolcke, Martin Graciarena, Nicolas Scheffer
  • Publication number: 20160086090
    Abstract: The present invention relates to a method and apparatus for tailoring the output of an intelligent automated assistant. One embodiment of a method for conducting an interaction with a human user includes collecting data about the user using a multimodal set of sensors positioned in a vicinity of the user, making a set of inferences about the user in accordance with the data, and tailoring an output to be delivered to the user in accordance with the set of inferences.
    Type: Application
    Filed: December 2, 2015
    Publication date: March 24, 2016
    Inventors: Gokhan Tur, Horacio E. Franco, Elizabeth Shriberg, Gregory K. Myers, William S. Mark, Norman D. Winarsky, Andreas Stolcke, Bart Peinter, Michael J. Wolverton, Luciana Ferrer, Martin Graciarena, Neil Yorke-Smith, Harry Bratt
  • Patent number: 9213558
    Abstract: The present invention relates to a method and apparatus for tailoring the output of an intelligent automated assistant. One embodiment of a method for conducting an interaction with a human user includes collecting data about the user using a multimodal set of sensors positioned in a vicinity of the user, making a set of inferences about the user in accordance with the data, and tailoring an output to be delivered to the user in accordance with the set of inferences.
    Type: Grant
    Filed: September 1, 2010
    Date of Patent: December 15, 2015
    Assignee: SRI INTERNATIONAL
    Inventors: Gokhan Tur, Horacio E. Franco, Elizabeth Shriberg, Gregory K. Myers, William S. Mark, Norman D. Winarsky, Andreas Stolcke, Bart Peintner, Michael J. Wolverton, Luciana Ferrer, Martin Graciarena, Harry Bratt, Neil Yorke-Smith
  • Patent number: 9147401
    Abstract: The present invention relates to a method and apparatus for speaker-calibrated speaker detection. One embodiment of a method for generating a speaker model for use in detecting a speaker of interest includes identifying one or more speech features that best distinguish the speaker of interest from a plurality of impostor speakers and then incorporating the speech features in the speaker model.
    Type: Grant
    Filed: December 21, 2011
    Date of Patent: September 29, 2015
    Assignee: SRI INTERNATIONAL
    Inventors: Elizabeth Shriberg, Luciana Ferrer, Andreas Stolcke, Martin Graciarena, Nicolas Scheffer
  • Publication number: 20130166295
    Abstract: The present invention relates to a method and apparatus for speaker-calibrated speaker detection. One embodiment of a method for generating a speaker model for use in detecting a speaker of interest includes identifying one or more speech features that best distinguish the speaker of interest from a plurality of impostor speakers and then incorporating the speech features in the speaker model.
    Type: Application
    Filed: December 21, 2011
    Publication date: June 27, 2013
    Inventors: ELIZABETH SHRIBERG, Luciana Ferrer, Andreas Stolcke, Martin Graciarena, Nicolas Scheffer
  • Publication number: 20120166365
    Abstract: The present invention relates to a method and apparatus for tailoring the output of an intelligent automated assistant. One embodiment of a method for conducting an interaction with a human user includes collecting data about the user using a multimodal set of sensors positioned in a vicinity of the user, making a set of inferences about the user in accordance with the data, and tailoring an output to be delivered to the user in accordance with the set of inferences.
    Type: Application
    Filed: September 1, 2010
    Publication date: June 28, 2012
    Inventors: Gokhan Tur, Horacio E. Franco, Elizabeth Shriberg, Gregory K. Myers, William S. Mark, Norman D. Winarsky, Andreas Stolcke, Bart Peintner, Michael J. Wolverton, Luciana Ferrer, Martin Graciarena, Neil Yorke-Smith
  • Patent number: 7769593
    Abstract: In one embodiment, the present invention is a method and apparatus for active noise cancellation. In one embodiment, a method for recognizing user speech in an audio signal received by a media system (where the audio signal includes user speech and ambient audio output produced by the media system and/or other devices) includes canceling portions of the audio signal associated with the ambient audio output and applying speech recognition processing to an uncancelled remainder of the audio signal.
    Type: Grant
    Filed: September 28, 2006
    Date of Patent: August 3, 2010
    Assignee: SRI International
    Inventors: Anand Venkataraman, Venkata Ramana Rao Gadde, Martin Graciarena
  • Patent number: 7571095
    Abstract: An apparatus and a concomitant method for recognizing speech in a noisy environment are provided. The present method includes applying a first interpolation weight to a clean speech model to produce a weighted clean speech model, applying a second interpolation weight to a noise model to produce a weighted noise model, and deriving a noisy speech model directly from the weighted clean speech model and the weighted noise model. At least one of the first interpolation weight and the second interpolation weight is computed in a maximum likelihood framework.
    Type: Grant
    Filed: August 31, 2005
    Date of Patent: August 4, 2009
    Assignee: SRI International
    Inventors: Martin Graciarena, Horacio Franco, Venkata Ramana Rao Gadde
  • Publication number: 20080082326
    Abstract: In one embodiment, the present invention is a method and apparatus for active noise cancellation. In one embodiment, a method for recognizing user speech in an audio signal received by a media system (where the audio signal includes user speech and ambient audio output produced by the media system and/or other devices) includes canceling portions of the audio signal associated with the ambient audio output and applying speech recognition processing to an uncancelled remainder of the audio signal.
    Type: Application
    Filed: September 28, 2006
    Publication date: April 3, 2008
    Inventors: Anand Venkataraman, Venkata Ramana Rao Gadde, Martin Graciarena
  • Publication number: 20080010065
    Abstract: A method and apparatus for speaker recognition is provided. One embodiment of a method for determining whether a given speech signal is produced by an alleged speaker, where a plurality of statistical models (including at least one support vector machine) have been produced for the alleged speaker based on a previous speech signal received from the alleged speaker, includes receiving the given speech signal, the speech signal representing an utterance made by a speaker claiming to be the alleged speaker, scoring the given speech signal using at least two modeling systems, where at least one of the modeling systems is a support vector machine, combining scores produced by the modeling systems, with equal weights, to produce a final score, and determining, in accordance with the final score, whether the speaker is likely the alleged speaker.
    Type: Application
    Filed: June 5, 2007
    Publication date: January 10, 2008
    Inventors: Harry BRATT, Luciana Ferrer, Martin Graciarena, Sachin Kajarekar, Elizabeth Shriberg, Mustafa Sonmez, Andreas Stolcke, Gokhan Tur, Anand Venkataraman
  • Publication number: 20060195317
    Abstract: An apparatus and a concomitant method for recognizing speech in a noisy environment are provided. The present method includes applying a first interpolation weight to a clean speech model to produce a weighted clean speech model, applying a second interpolation weight to a noise model to produce a weighted noise model, and deriving a noisy speech model directly from the weighted clean speech model and the weighted noise model. At least one of the first interpolation weight and the second interpolation weight is computed in a maximum likelihood framework.
    Type: Application
    Filed: August 31, 2005
    Publication date: August 31, 2006
    Inventors: Martin Graciarena, Horacio Franco, Venkata Gadde