Patents by Inventor Simon Graf

Simon Graf 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: 10342923
    Abstract: The present disclosure relates to a control system for controlling a medical system. The control system comprising: a portable device, a transmitter placed in a location of a local use environment of the portable device, and a data handling system comprising a detection module, a data interface, and a device controller functionally connected to the detection module and the data interface. The data handling system is configured to detect local vicinity of the portable device to the at least one transmitter by the detection module, receive input data from the at least one transmitter via the data interface, generate device control data for a medical device, comprising processing of the input data, and transmitting the device control data to a control device. Furthermore, a portable device, a method for controlling a medical system, and a computer program product for controlling a medical system by a control system are disclosed.
    Type: Grant
    Filed: December 19, 2017
    Date of Patent: July 9, 2019
    Assignee: ROCHE DIABETES CARE, INC.
    Inventors: Annika Henrich, Til Rendschmidt, Markus Graf, Tobias Loerracher, Simon Wetzel
  • Patent number: 10332545
    Abstract: A method, computer program product, and computer system for receiving, by a computing device, a speech signal from a speaker via a plurality of microphone zones. A temporal cue based confidence may be determined for at least a portion of the plurality of microphone zones. A power cue based confidence may be determined for at least a portion of the plurality of microphone zones. A microphone zone of the plurality of microphone zones from which to use an output signal of the speaker may be identified based upon, at least in part, a combination of the temporal cue based confidence and the power cue based confidence.
    Type: Grant
    Filed: November 28, 2017
    Date of Patent: June 25, 2019
    Assignee: Nuance Communications, Inc.
    Inventors: Timo Matheja, Markus Buck, Simon Graf
  • Publication number: 20190164568
    Abstract: A method, computer program product, and computer system for receiving, by a computing device, a speech signal from a speaker via a plurality of microphone zones. A temporal cue based confidence may be determined for at least a portion of the plurality of microphone zones. A power cue based confidence may be determined for at least a portion of the plurality of microphone zones. A microphone zone of the plurality of microphone zones from which to use an output signal of the speaker may be identified based upon, at least in part, a combination of the temporal cue based confidence and the power cue based confidence.
    Type: Application
    Filed: November 28, 2017
    Publication date: May 30, 2019
    Inventors: Timo Matheja, Markus Buck, Simon Graf
  • Publication number: 20190163835
    Abstract: A computer program product, system, and method for building a knowledge graph may include receiving a plurality of new nodes, receiving a base knowledge graph having existing nodes selectively connected by existing edges, and superimposing the new nodes onto selected ones of the existing nodes of the base knowledge graph. The method may further include connecting the new nodes by creating a new edge with a new weight between at least two of the new nodes if corresponding existing nodes in the underlying base knowledge graph have a connection via zero or a predetermined maximum number of existing edges, wherein the new weight is determined based on the existing weights of the existing edges of connections between the corresponding existing nodes, and detaching the new nodes with the new edges from the base knowledge graph.
    Type: Application
    Filed: November 27, 2017
    Publication date: May 30, 2019
    Inventors: Tim U. Scheideler, Stefan Ravizza, Andrea Giovannini, Avdyl Haxhaj, Simon Streit, Florian Graf
  • Publication number: 20190164542
    Abstract: A method, computer program product, and computer system for receiving, by a computing device, a first signal emitted from one or more sources. A second signal may be received emitted from the one or more sources. A first confidence level that the wake-up-word is included in the first signal may be determined. A second confidence level that the wake-up-word is included in the second signal may be determined. It may be identified that the wake-up-word originated from a first source of the one or more sources based upon, at least in part, the first and second confidence levels. The first source may be enabled to participate in a dialogue phase.
    Type: Application
    Filed: December 5, 2017
    Publication date: May 30, 2019
    Inventors: Tobias Wolff, Jan Philip Janssen, Simon Graf, Tim Haulick
  • Publication number: 20190139567
    Abstract: Speech processing methods may rely on voice activity detection (VAD) that separates speech from noise. Example embodiments of a computationally low complex VAD feature that is robust against various types of noise is introduced. By considering an alternating excitation structure of low and high frequencies, speech is detected with a high confidence. The computationally low complex VAD feature can cope even with the limited spectral resolution that may be typical for a communication system, such as an in-car-communication (ICC) system. Simulation results confirm the robustness of the computationally low complex VAD feature and show an increase in performance relative to established VAD features.
    Type: Application
    Filed: February 17, 2017
    Publication date: May 9, 2019
    Inventors: Simon Graf, Tobias Herbig, Markus Buck
  • Patent number: 10229686
    Abstract: Methods and apparatus to process microphone signals by a speech enhancement module to generate an audio stream signal including first and second metadata for use by a speech recognition module. In an embodiment, speech recognition is performed using endpointing information including transitioning from a silence state to a maybe speech state, in which data is buffered, based on the first metadata and transitioning to a speech state, in which speech recognition is performed, based upon the second metadata.
    Type: Grant
    Filed: August 18, 2014
    Date of Patent: March 12, 2019
    Assignee: NUANCE COMMUNICATIONS, INC.
    Inventors: Markus Buck, Tobias Herbig, Simon Graf, Christophe Ris
  • Publication number: 20190013036
    Abstract: Systems and methods are introduced to perform noise suppression of an audio signal. The audio signal includes foreground speech components and background noise. The foreground speech components correspond to speech from a user's speaking into an audio receiving device. The background noise includes babble noise that includes speech from one or more interfering speakers. A soft speech detector determines, dynamically, a speech detection result indicating a likelihood of a presence of the foreground speech components in the audio signal. The speech detection result is employed to control, dynamically, an amount of attenuation of the noise suppression to reduce the babble noise in the audio signal. Further processing achieves a more stationary background and reduction of musical tones in the audio signal.
    Type: Application
    Filed: November 18, 2016
    Publication date: January 10, 2019
    Inventors: Simon Graf, Tobias Herbig, Markus Buck
  • Patent number: 10157611
    Abstract: A method, computer program product, and computer system for receiving, by a computing device, a first signal emitted from one or more sources. A second signal may be received emitted from the one or more sources. A first confidence level that the wake-up-word is included in the first signal may be determined. A second confidence level that the wake-up-word is included in the second signal may be determined. It may be identified that the wake-up-word originated from a first source of the one or more sources based upon, at least in part, the first and second confidence levels. The first source may be enabled to participate in a dialog phase. The second source may be excluded from participating in the dialog phase.
    Type: Grant
    Filed: November 29, 2017
    Date of Patent: December 18, 2018
    Assignee: Nuance Communications, Inc.
    Inventors: Tobias Wolff, Jan Philip Janssen, Simon Graf, Tim Haulick
  • Publication number: 20170213556
    Abstract: Methods and apparatus to process microphone signals by a speech enhancement module to generate an audio stream signal including first and second metadata for use by a speech recognition module. In an embodiment, speech recognition is performed using endpointing information including transitioning from a silence state to a maybe speech state, in which data is buffered, based on the first metadata and transitioning to a speech state, in which speech recognition is performed, based upon the second metadata.
    Type: Application
    Filed: August 18, 2014
    Publication date: July 27, 2017
    Applicant: NUANCE COMMUNICATIONS, INC.
    Inventors: Markus BUCK, Tobias HERBIG, Simon GRAF, Christophe RIS
  • Publication number: 20170079747
    Abstract: An orthodontic apparatus (1; 10) is designed with at least one orthodontically effective element (4; 12) and at least one holding element (5; 13) for holding the apparatus (1; 10) on the jaw, whereby the apparatus (1;10) is designed in one piece. In a method for producing an orthodontic apparatus, an electronic data set is produced for a three-dimensional model (2) of a jaw to which the apparatus is supposed to be attached. Further, a virtual positioning of one or more orthodontic elements (4; 12) of the apparatus on jaw model (2) takes place. An electronic data set of a three-dimensional model (3; 11) of the apparatus is subsequently produced. The apparatus (1; 10) is then produced by an additive and/or removal production method according to the data set of the apparatus model.
    Type: Application
    Filed: May 20, 2015
    Publication date: March 23, 2017
    Inventors: Simon Graf, Roland Kiss, Mark Kabashi
  • Publication number: 20150369297
    Abstract: An elastic coupling, in particular an elastic shaft coupling, includes a metallic outer part, a metallic inner part and elastic buffers arranged so as to be spaced apart between the outer part and the inner part. The outer part includes radially inwardly projecting elevations which define buffer contact surfaces and the inner part includes radially outwardly projecting elevations which define buffer contact surfaces. In order for the elastic coupling to allow for gentler startup and an operating behaviour optimized in terms of rotary oscillation in comparison with conventional couplings of this type. The elastic buffers are arranged in at least two groups which are radially spaced apart. At least one annular intermediate part is arranged between the adjacent buffer groups and is connected torsionally to both the outer part and to the inner part via the elastic buffers.
    Type: Application
    Filed: January 14, 2014
    Publication date: December 24, 2015
    Applicant: RINGFEDER POWER TRANSMISSION TSCHAN GMBH
    Inventors: Simon Graf, G√ľnter Lamber
  • Patent number: 7529068
    Abstract: The voltage of the intermediate circuit of a frequency converter is monitored, while the intermediate circuit is charged via charging resistors. When the voltage has not reached at least a reference voltage during a specific time constant, the charging process is interrupted prematurely. The reference voltage is selected to be considerably lower than the operating voltage of the intermediate circuit. The reference voltage may be less than half of the operating voltage of the intermediate circuit.
    Type: Grant
    Filed: April 25, 2005
    Date of Patent: May 5, 2009
    Assignee: Dr. Johannes Heidenhain GmbH
    Inventors: Norbert Huber, Simon Graf
  • Publication number: 20050237679
    Abstract: The voltage of the intermediate circuit of a frequency converter is monitored, while the intermediate circuit is charged via charging resistors. When the voltage has not reached at least a reference voltage during a specific time constant, the charging process is interrupted prematurely. The reference voltage is selected to be considerably lower than the operating voltage of the intermediate circuit. The reference voltage may be less than half of the operating voltage of the intermediate circuit.
    Type: Application
    Filed: April 25, 2005
    Publication date: October 27, 2005
    Inventors: Norbert Huber, Simon Graf
  • Patent number: 5131017
    Abstract: An evaluation device with an absolute value counter is provided in an incremental position measuring system, which determines the absolute position even in case of loss of the main power supply. The evaluation device is operated by means of an emergency power supply while the main power supply is out. Following the restoration of the main power supply, counting pulses are supplied to a follow-up counter (11) by a pulse emitter, until the follow-up counter has reached the counter reading of the absolute value counter. Two rectangular signals, which are phase-shifted by 90.degree. in relation to each other, are formed as a function of the counting signals, which are present at the evaluation device in the form of output signals.
    Type: Grant
    Filed: April 8, 1991
    Date of Patent: July 14, 1992
    Assignee: Dr. Johannes Heidenhain GmbH
    Inventors: Norbert Huber, Simon Graf