Patents by Inventor Krishna Kamath Koteshwara

Krishna Kamath Koteshwara 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: 11402499
    Abstract: This disclosure describes presence-detection devices that detect movement of a person by emitting ultrasonic signals into an environment, and characterizing the change in the frequency, or the Doppler shift, of the reflections of the ultrasonic signals off the person caused by the movement of the person. The techniques include downsampling the audio signals from the carrier frequency range down to a frequency range with a center frequency around 0 Hz. A filter is applied to attenuate signals around 0 Hz and below (or above), such as the emitted signals. In addition to removing the emitted signals, the negative side (or positive side) of the audio signals are removed, but the Doppler shift is still represented in the remaining portion of the audio signals. By removing a portion of the audio signals, the amount of processing required to detect the Doppler shift in the reflections of the ultrasonic signals is reduced.
    Type: Grant
    Filed: September 9, 2020
    Date of Patent: August 2, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Krishna Kamath Koteshwara, Tarun Pruthi, Ke Li
  • Patent number: 10937418
    Abstract: A system configured to improve echo cancellation for nonlinear systems. The system generate reference audio data by isolating portions of microphone audio data that correspond to playback audio data. For example, the system may determine a correlation between the playback audio data and the microphone audio data in individual time-frequency bands in a frequency domain. In some examples, the system may substitute microphone audio data associated with output audio for the playback audio data. The system may generate the reference audio data based on portions of the microphone audio data that have a strong correlation with the playback audio data. The system may generate the reference audio data by selecting these portions of the microphone audio data or by performing beamforming. This results in precise time alignment between the reference audio data and the microphone audio data, improving performance of the echo cancellation.
    Type: Grant
    Filed: January 4, 2019
    Date of Patent: March 2, 2021
    Assignee: Amazon Technologies, Inc.
    Inventors: Navin Chatlani, Krishna Kamath Koteshwara, Trausti Thor Kristjansson, Inseok Heo, Robert Ayrapetian
  • Patent number: 10795018
    Abstract: This disclosure describes presence-detection devices that detect movement of a person in an environment by emitting ultrasonic signals into the environment, and characterizing the change in the frequency, or the Doppler shift, of the reflections of the ultrasonic signals off the person caused by the movement of the person. In addition to detecting movement, and thus presence of a person, the presence-detection devices may include a microphone array to perform techniques for identifying a direction of movement of the person, and also to perform techniques for identifying a number of people that are in the room. Additionally, the techniques described herein include processing audio signals in such a way to allow for the use of on-board loudspeakers to transmit ultrasonic signals at out-of-band frequencies.
    Type: Grant
    Filed: August 29, 2018
    Date of Patent: October 6, 2020
    Assignee: Amazon Technologies, Inc.
    Inventor: Krishna Kamath Koteshwara
  • Patent number: 10127918
    Abstract: A system configured to reconstruct audio signals. The system may identify missing audio samples due to packet loss or detect distortion caused by audio clipping and may reconstruct the audio data. The system may employ a forward-looking neural network that recursively predicts audio samples based on previous audio samples and/or a backward-looking neural network that recursively predicts audio samples based on subsequent audio samples. The system may generate audio data using only the forward-looking neural network for low latency applications or may generate audio data using both neural networks for mid to high latency applications. To reduce distortion in output audio data, the system may generate the audio data by cross-fading between outputs of the neural networks and/or may cross-fade between the generated audio data and the input audio data.
    Type: Grant
    Filed: May 3, 2017
    Date of Patent: November 13, 2018
    Assignee: Amazon Technologies, Inc.
    Inventors: Krishna Kamath Koteshwara, Trausti Thor Kristjansson
  • Patent number: 9947338
    Abstract: A device that determines an echo latency estimate by combining reference signals. The device may determine the echo latency corresponding to an amount of time between reference signals being sent to transmitters and input data corresponding to the reference signals being received. The device may generate a combined reference signal by adding (or filtering) each of the reference signals. The device may then compare the combined reference signal to input audio data received from a microphone or receiving device. The device may detect a highest peak, determine if there are any earlier significant peaks and estimate the echo latency based on the earliest significant peak. This technique is not limited to audio data and may be used for signal matching using any system that includes multiple transmitters and receivers (e.g., Radar, Sonar, etc.).
    Type: Grant
    Filed: September 19, 2017
    Date of Patent: April 17, 2018
    Assignee: Amazon Technologies, Inc.
    Inventors: Krishna Kamath Koteshwara, Trausti Thor Kristjansson
  • Patent number: 9548048
    Abstract: A speech recognition computer system uses video input as well as audio input of known speech when the speech recognition computer system is being trained to recognize unknown speech. The video of the speaker can be captured using multiple cameras, from multiple angles. The audio can be captured using multiple microphones. The video and audio can be sampled so that timing of events in the video and audio can be determined from the content independent of an audio or video capture device's clock. Video features, such as a speaker's moving body parts, can be extracted from the video and random sampled, to be used in a speech modeling process. Audio is modeled at the phoneme level, which provides word mapping with minor additional effort. The trained speech recognition computer system can then be used to recognize speech text from video/audio of unknown speech.
    Type: Grant
    Filed: June 19, 2015
    Date of Patent: January 17, 2017
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Mashhour Solh, Krishna Kamath Koteshwara
  • Patent number: 9424456
    Abstract: An ultrasonic finger print authentication system that generates a three-dimensional representation of a fingerprint. High frequency sound waves are used as a medium for imaging finer details of the patterns on a fingertip, including the ridge and valley formations. Multiple frequencies and beam-forming are used to quickly map the ridges. Acoustic resonance is used to determine the depths of the intervening valleys.
    Type: Grant
    Filed: June 24, 2015
    Date of Patent: August 23, 2016
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Krishna Kamath Koteshwara, Pushkaraksha Gejji