Patents by Inventor Harsha Inna Kedage Rao
Harsha Inna Kedage Rao 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: 11727912Abstract: A system configured to perform deep adaptive acoustic echo cancellation (AEC) to improve audio processing. Due to mechanical noise and continuous echo path changes caused by movement of a device, echo signals are nonlinear and time-varying and not fully canceled by linear AEC processing alone. To improve echo cancellation, deep adaptive AEC processing integrates a deep neural network (DNN) and linear adaptive filtering to perform echo and/or noise removal. The DNN is configured to generate a nonlinear reference signal and step-size data, which the linear adaptive filtering uses to generate output audio data representing local speech. The DNN may generate the nonlinear reference signal by generating mask data that is applied to a microphone signal, such that the reference signal corresponds to a portion of the microphone signal that does not include near-end speech.Type: GrantFiled: March 29, 2022Date of Patent: August 15, 2023Assignee: Amazon Technologies, Inc.Inventors: Harsha Inna Kedage Rao, Srivatsan Kandadai, Minje Kim, Tarun Pruthi, Trausti Thor Kristjansson
-
Patent number: 11614529Abstract: Techniques for presence-detection devices to emission levels of ultrasonic signals that are used to detect movement in an environment. The presence-detection devices may detect movement of a person by emitting the 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 relative to the presence-detection devices. However, presence-detection devices that continuously emit ultrasonic signals may experience reduced battery life, increased likelihood of overheating, etc. To reduce these negative effects, the presence-detection devices may reduce the emission levels of ultrasonic signals. For instance, once motion is detected, the presence-detection devices may, for a period of time, stop emitting ultrasonic signals or reduce the power level at which the ultrasonic signals are emitted.Type: GrantFiled: March 19, 2021Date of Patent: March 28, 2023Assignee: Amazon Technologies, Inc.Inventors: Harsha Inna Kedage Rao, Maziyar Khorasani, Tarun Pruthi, Krishna Kamath Koteshwara
-
Patent number: 9668048Abstract: Provided are systems and methods for contextual switching of microphones in audio devices. An example method includes detecting a change in conditions for capturing an acoustic signal by at least two microphones. A configuration is associated with the at least two microphones. The example method provides determining that the change in conditions has been stable for a pre-determined period of time. In response to the determination, the method changes the configuration associated with the at least two microphones. The conditions may include an absence or presence of far-end speech, reverberation, low/high signal-to-noise ratio, low/high signal-to-echo ratio, type of background noise, and so on. The changing of the configuration includes assigning a primary microphone and a secondary microphone based on a change in conditions. Based on the changed configuration, tuning parameters may be adjusted for noise suppression and acoustic echo cancellation.Type: GrantFiled: January 29, 2016Date of Patent: May 30, 2017Assignee: Knowles Electronics, LLCInventors: Shailesh Sakri, Ajay Kumar Dhanapalan, Harsha Inna Kedage Rao
-
Patent number: 9589550Abstract: Various embodiments relate to determining an energy level of one or more sound components from a sound mix. Based on at least one sound mix signal received from a mixing device and at least one component signal received from one or more sound components, at least one signal value of the sound mix signal and at least one signal value of the component signal may be computed. The component signal corresponds to each of the one or more sound components. An energy level of the one or more sound components may be determined based on the sound mix signal value and the component signal value which corresponds to each of the one or more sound components. The energy level of the one or more sound components may be output in order to determine the energy level of each component in the sound mix.Type: GrantFiled: September 30, 2011Date of Patent: March 7, 2017Assignee: HARMAN INTERNATIONAL INDUSTRIES, INC.Inventors: James Kirsch, Harsha Inna Kedage Rao
-
Publication number: 20160227336Abstract: Provided are systems and methods for contextual switching of microphones in audio devices. An example method includes detecting a change in conditions for capturing an acoustic signal by at least two microphones. A configuration is associated with the at least two microphones. The example method provides determining that the change in conditions has been stable for a pre-determined period of time. In response to the determination, the method changes the configuration associated with the at least two microphones. The conditions may include an absence or presence of far-end speech, reverberation, low/high signal-to-noise ratio, low/high signal-to-echo ratio, type of background noise, and so on. The changing of the configuration includes assigning a primary microphone and a secondary microphone based on a change in conditions. Based on the changed configuration, tuning parameters may be adjusted for noise suppression and acoustic echo cancellation.Type: ApplicationFiled: January 29, 2016Publication date: August 4, 2016Inventors: Shailesh Sakri, Ajay Kumar Dhanapalan, Harsha Inna Kedage Rao
-
Patent number: 9060237Abstract: Systems and method for performing adaptive audio signal processing using music as a measurement stimulus signal. A musical stimuli generator may be used to generate musical stimulus signals composed to provide a stimulus with a spectrum that is substantially dense, and ideally white or pink, over a selected frequency range, so that all frequencies of interest are stimulated. The musical stimuli generator may generate melodically pleasing musical stimulus signals using music clips that include any of: a chromatic sequence, a chromatic sequence including chromatic tones over a plurality of octaves, a chromatic sequence including chromatic tones over a selected plurality of octaves, or an algorithmically composed chromatic sequence, to cover a selected frequency range. The musical stimulus signal may be generated as sound into the environment of use. An audio input picks up the sound from the environment, and a sound processor uses the received musical stimulus signal to determine a transfer function.Type: GrantFiled: June 29, 2011Date of Patent: June 16, 2015Assignee: Harman International Industries, IncorporatedInventors: James Kirsch, Harsha Inna Kedage Rao
-
Patent number: 8884149Abstract: Systems and method for performing adaptive audio signal processing using music as a measurement stimulus signal. A musical stimuli generator may be used to generate musical stimulus signals composed to provide a stimulus with a spectrum that is substantially dense, and ideally white or pink, over a selected frequency range, so that all frequencies of interest are stimulated. The musical stimuli generator may generate melodically pleasing musical stimulus signals using music clips that include any of: a chromatic sequence, a chromatic sequence including chromatic tones over a plurality of octaves, a chromatic sequence including chromatic tones over a selected plurality of octaves, or an algorithmically composed chromatic sequence, to cover a selected frequency range. The musical stimulus signal may be generated as sound into the environment of use. An audio input picks up the sound from the environment, and a sound processor uses the received musical stimulus signal to determine a transfer function.Type: GrantFiled: June 29, 2011Date of Patent: November 11, 2014Assignee: Harman International Industries, IncorporatedInventors: James Kirsch, Harsha Inna Kedage Rao
-
Publication number: 20130083932Abstract: Various embodiments relate to determining an energy level of one or more sound components from a sound mix. Based on at least one sound mix signal received from a mixing device and at least one component signal received from one or more sound components, at least one signal value of the sound mix signal and at least one signal value of the component signal may be computed. The component signal corresponds to each of the one or more sound components. An energy level of the one or more sound components may be determined based on the sound mix signal value and the component signal value which corresponds to each of the one or more sound components. The energy level of the one or more sound components may be output in order to determine the energy level of each component in the sound mix.Type: ApplicationFiled: September 30, 2011Publication date: April 4, 2013Applicant: Harman International Industries, IncorporatedInventors: James Kirsch, Harsha Inna Kedage Rao
-
Publication number: 20130000464Abstract: Systems and method for performing adaptive audio signal processing using music as a measurement stimulus signal. A musical stimuli generator may be used to generate musical stimulus signals composed to provide a stimulus with a spectrum that is substantially dense, and ideally white or pink, over a selected frequency range, so that all frequencies of interest are stimulated. The musical stimuli generator may generate melodically pleasing musical stimulus signals using music clips that include any of: a chromatic sequence, a chromatic sequence including chromatic tones over a plurality of octaves, a chromatic sequence including chromatic tones over a selected plurality of octaves, or an algorithmically composed chromatic sequence, to cover a selected frequency range. The musical stimulus signal may be generated as sound into the environment of use. An audio input picks up the sound from the environment, and a sound processor uses the received musical stimulus signal to determine a transfer function.Type: ApplicationFiled: June 29, 2011Publication date: January 3, 2013Applicant: Harman International Industries, IncorporatedInventors: James Kirsch, Harsha Inna Kedage Rao