Patents by Inventor Ashutosh Pandey

Ashutosh Pandey 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: 20140278417
    Abstract: Methods, systems, and apparatuses are described for performing speaker-identification-assisted speech processing. In accordance with certain embodiments, a communication device includes speaker identification (SID) logic that is configured to identify a user of the communication device and/or the identity of a far-end speaker participating in a voice call with a user of the communication device. Knowledge of the identity of the user and/or far-end speaker is then used to improve the performance of one or more speech processing algorithms implemented on the communication device.
    Type: Application
    Filed: August 13, 2013
    Publication date: September 18, 2014
    Applicant: Broadcom Corporation
    Inventors: Juin-Hwey Chen, Robert W. Zopf, Bengt J. Borgstrom, Elias Nemer, Ashutosh Pandey, Jes Thyssen
  • Publication number: 20140278418
    Abstract: Methods, systems, and apparatuses are described for performing speaker-identification-assisted speech processing in a downlink path of a communication device. In accordance with certain embodiments, a communication device includes speaker identification (SID) logic that is configured to identify the identity of a far-end speaker participating in a voice call with a user of the communication device. Knowledge of the identity of the far-end speaker is then used to improve the performance of one or more downlink speech processing algorithms implemented on the communication device.
    Type: Application
    Filed: September 30, 2013
    Publication date: September 18, 2014
    Inventors: Juin-Hwey Chen, Robert W. Zopf, Bengt J. Borgstrom, Elias Nemer, Ashutosh Pandey, Jes Thyssen
  • Publication number: 20140278397
    Abstract: Methods, systems, and apparatuses are described for performing speaker-identification-assisted speech processing in an uplink path of a communication device. In accordance with certain embodiments, a communication device includes speaker identification (SID) logic that is configured to identify the identity of a near-end speaker. Knowledge of the identity of the near-end speaker is then used to improve the performance of one or more uplink speech processing algorithms implemented on the communication device.
    Type: Application
    Filed: October 31, 2013
    Publication date: September 18, 2014
    Applicant: Broadcom Corporation
    Inventors: Juin-Hwey Chen, Jes Thyssen, Elias Nemer, Bengt J. Borgstrom, Ashutosh Pandey, Robert W. Zopf
  • Patent number: 8630437
    Abstract: Adaptive notch filters can be used to estimate offending frequencies caused by feedback within a hearing aid system. The offending frequencies can be suppressed by filtering. Offending frequencies can be identified based on variability of the adaptive notch filter parameters.
    Type: Grant
    Filed: February 22, 2011
    Date of Patent: January 14, 2014
    Assignee: University of Utah Research Foundation
    Inventors: Ashutosh Pandey, V. John Mathews
  • Publication number: 20130094653
    Abstract: Voice over internet protocol (VoIP) devices and conferencing systems may include a spatial encoder associated with a first endpoint and a spatial renderer associated with a second endpoint. The spatial renderer may configured to receive audio data. The audio data may be rendered among a plurality of speakers based on a first set of spatial information for a plurality of microphones associated with the first endpoint, and a second set of spatial information for the plurality of speakers associated with the second endpoint. A method for generating a sound field may include determining spatial information for a plurality of microphones in a local room, determining spatial information for a plurality of speakers in a remote room, mapping the spatial information for the plurality of microphones and the spatial information for the plurality of speakers, and generating a sound field in the remote room based on the mapping.
    Type: Application
    Filed: June 11, 2012
    Publication date: April 18, 2013
    Applicant: CLEARONE COMMUNICATIONS, INC.
    Inventors: Tracy A. Bathurst, Derek Graham, Michael Braithwaite, Russel S. Ericksen, Brett Harris, Sandeep Kalra, David K. Lambert, Peter H. Manley, Ashutosh Pandey, Bryan Shaw, Michael Tilelli, Paul R. Bryson
  • Publication number: 20130097333
    Abstract: Embodiments include methods, computer-readable media, and apparatuses for supporting unified streaming communications. A communication apparatus is configured to communicate over a network to incorporate a wide variety of protocols and peripheral devices for use in audio, video, and media communication systems.
    Type: Application
    Filed: June 12, 2012
    Publication date: April 18, 2013
    Applicant: CLEARONE COMMUNICATIONS, INC.
    Inventors: Tracy A. Bathurst, Derek Graham, Michael Braithwaite, Russel S. Ericksen, Brett Harris, Sandeep Kalra, David K. Lambert, Peter H. Manley, Ashutosh Pandey, Bryan Shaw, Darrin T. Thurston, Michael Tilelli, Paul R. Bryson
  • Publication number: 20130083911
    Abstract: Embodiments include methods and apparatuses for echo cancelation involving multiple audio channels and the production, sensing, or a combination thereof of multiple audio channels in conferencing systems. A conferencing apparatus with a plurality of speakers configured to generate outgoing acoustic waves responsive to a multi-channel audio signal. One or more microphones are configured to sense incoming acoustic waves from the plurality of speakers and from locally produced acoustic waves from a participant of a conference to generate one or more incoming audio signals. A processor is operably coupled to the plurality of speakers and the one or more microphones. The processor is configured to perform acoustic echo cancelation on the one or more incoming audio signals relative to at least two different channels of the multi-channel audio signal.
    Type: Application
    Filed: June 11, 2012
    Publication date: April 4, 2013
    Applicant: ClearOne Communications, Inc.
    Inventors: Tracy A. Bathurst, Derek Graham, Michael Braithwaite, Russel S. Ericksen, Brett Harris, Sandeep Kalra, David K. Lambert, Peter H. Manley, Ashutosh Pandey, Bryan Shaw, Michael Tilelli, Paul R. Bryson
  • Publication number: 20130039504
    Abstract: Embodiments include methods and apparatuses for sensing acoustic waves for a conferencing application. A conferencing apparatus includes a plurality of microphones oriented to cover a corresponding plurality of direction vectors and to develop a corresponding plurality of microphone signals. A processor is operably coupled to the plurality of microphones. The processor is configured to perform a beamforming operation to combine the plurality of microphone signals to a plurality of combined signals that is greater in number than one and less in number than the plurality of microphone signals. The processor is also configured perform an acoustic echo cancelation operation on the plurality of combined signals to generate a plurality of combined echo-canceled signals and select one of the plurality of combined echo-canceled signals for transmission.
    Type: Application
    Filed: June 11, 2012
    Publication date: February 14, 2013
    Applicant: CLEARONE COMMUNICATIONS, INC.
    Inventors: Ashutosh Pandey, Darrin T. Thurston, David K. Lambert, Tracy A. Bathurst
  • Publication number: 20130034241
    Abstract: Embodiments include methods and apparatuses for sensing acoustic waves for a conferencing application. A conferencing apparatus includes a plurality of directional microphones oriented to cover a corresponding plurality of direction vectors and disposed in a housing. An orientation sensor is configured to generate an orientation signal indicative of an orientation of the housing. A processor is operably coupled to the plurality of directional microphones and the orientation sensor. The processor is configured to automatically adjust a signal processing characteristic of one or more directional microphones of the plurality of directional microphones responsive to the orientation signal.
    Type: Application
    Filed: June 11, 2012
    Publication date: February 7, 2013
    Applicant: CLEARONE COMMUNICATIONS, INC.
    Inventors: Ashutosh Pandey, Darrin T. Thurston, David K. Lambert, Tracy A. Bathurst
  • Publication number: 20120293602
    Abstract: An executive telepresence system for use in audio and video conferencing uses a unified communications system in an enterprise network system. The executive telepresence system includes a control system that further comprises a user interface, a mixing system, and a dialing system. In addition, the executive telepresence system includes one or more video display devices that couple to the control system where the video display devices display a video signal, and may further include one or more video cameras that couple to the control system where the video cameras capture video information and turn it into the video signal. Further, the executive telepresence system includes one or more microphones that couple to the control system where the microphones capture audio information and turn it into an audio signal, and may include one or more speakers that couple to the control system where the speakers play back the audio signal.
    Type: Application
    Filed: February 16, 2012
    Publication date: November 22, 2012
    Applicant: CLEARONE COMMUNICATIONS, INC.
    Inventors: Tracy A. Bathurst, Derek Graham, Michael Braithwaite, Russell S. Ericksen, Bret Harris, Sandeep Kalra, David K. Lambert, Peter H. Manley, Ashutosh Pandey, Bryan Shaw, Darrin T. Thurston, Michael Tilelli, Paul R. Bryson
  • Patent number: 8103019
    Abstract: Disclosed herein are detectors of audio ringing feedback, that is decaying feedback with a gain of less than one, those detectors utilizing a repeated gain measurement that applied to a range of gain values characteristic of ringing-type feedback. Those gain measurements, while in the range, increase a probability measurement of feedback. When the probability of feedback reaches a threshold, a detection of feedback is made and feedback countermeasures, such as the application of a notch filter, may be applied. Optionally, the audio gain around likely frequencies of feedback may be enhanced for a time to increase the resolution of identification of a feedback frequency, which may be identified through an interpolative method. Repeated gain measurements may also identify building-type feedback. A ringing detector may include more than one range of detection, for example for building, strong-ringing and weak-ringing feedback.
    Type: Grant
    Filed: October 8, 2008
    Date of Patent: January 24, 2012
    Assignee: Clearone Comminications, Inc.
    Inventors: Ashutosh Pandey, David Lambert
  • Patent number: 8090118
    Abstract: Disclosed herein are detectors of audio ringing feedback, that is decaying feedback with a gain of less than one, those detectors utilizing a repeated gain measurement that applied to a range of gain values characteristic of ringing-type feedback. Those gain measurements, while in the range, increase a probability measurement of feedback. When the probability of feedback reaches a threshold, a detection of feedback is made and feedback countermeasures, such as the application of a notch filter, may be applied. Optionally, the audio gain around likely frequencies of feedback may be enhanced for a time to increase the resolution of identification of a feedback frequency, which may be identified through an interpolative method. Repeated gain measurements may also identify building-type feedback. A ringing detector may include more than one range of detection, for example for building, strong-ringing and weak-ringing feedback.
    Type: Grant
    Filed: October 8, 2008
    Date of Patent: January 3, 2012
    Assignee: ClearOne Communications, Inc.
    Inventors: Ashutosh Pandey, David Lambert
  • Patent number: 8027486
    Abstract: Disclosed herein are detectors of audio ringing feedback, that is decaying feedback with a gain of less than one, those detectors utilizing a repeated gain measurement that applied to a range of gain values characteristic of ringing-type feedback. Those gain measurements, while in the range, increase a probability measurement of feedback. When the probability of feedback reaches a threshold, a detection of feedback is made and feedback countermeasures, such as the application of a notch filter, may be applied. Optionally, the audio gain around likely frequencies of feedback may be enhanced for a time to increase the resolution of identification of a feedback frequency, which may be identified through an interpolative method. Repeated gain measurements may also identify building-type feedback. A ringing detector may include more than one range of detection, for example for building, strong-ringing and weak-ringing feedback.
    Type: Grant
    Filed: October 8, 2008
    Date of Patent: September 27, 2011
    Assignee: Clearone Communications, Inc.
    Inventors: Ashutosh Pandey, David Lambert
  • Publication number: 20110206226
    Abstract: Adaptive notch filters can be used to estimate offending frequencies caused by feedback within a hearing aid system. The offending frequencies can be suppressed by filtering. Offending frequencies can be identified based on variability of the adaptive notch filter parameters.
    Type: Application
    Filed: February 22, 2011
    Publication date: August 25, 2011
    Applicant: UNIVERSITY OF UTAH
    Inventors: Ashutosh Pandey, V. John Mathews