Patents by Inventor Sorin V. Dusan
Sorin V. Dusan 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: 20240363094Abstract: A conversation detector processes microphone signals and other sensor signals of a headphone to declare a conversation and configures a filter block to activate a transparency audio signal. It then declares an end to the conversation based on processing one or more of the microphone signals and the other sensor signals, and in response deactivates the transparency audio signal. The conversation detector monitors an idle duration in which an OVAD and a TVAD are both or simultaneously indicating no activity and declares the end to the conversation in response to the idle duration being longer than an idle threshold. Other aspects are also described and claimed.Type: ApplicationFiled: March 29, 2024Publication date: October 31, 2024Inventors: Ashok Masilamani, Prateek Murgai, John Woodruff, David M. Fischer, Jonathan D. Sheaffer, Jonathan Huang, Sorin V. Dusan, Andrew W. Malta, Erik D. Hornberger, Yichi Zhang, Miquel Espi Marques, Carlos M. Avendano
-
Publication number: 20240292151Abstract: Implementations of the subject technology provide systems and methods for providing distributed audio processing for audio devices. Distributed audio processing may include encoding signals from multiple microphones and/or sensors, such as at a headphone or an earbud, and decoding and processing the signals on host, source, or companion device. Distributed audio processing may also include deactivating one or more digital signal processors and/or neural networks based on an operational mode of an audio device or based on a processing capability of a companion device.Type: ApplicationFiled: December 21, 2023Publication date: August 29, 2024Inventors: Sorin V. DUSAN, Andreas KOUTROUVELIS, Sungyub D. Yoo, Sarthak Khanal, Tony S. VERMA
-
Patent number: 11948561Abstract: A signal processing method to determine whether or not a detected key-phrase is spoken by a wearer of a headphone. The method receives an accelerometer signal from an accelerometer in a headphone and receives a microphone signal from at least one microphone in the headphone. The method detects a key-phrase using the microphone signal and generates a voice activity detection (VAD) signal based on the accelerometer signal. The method determines whether the VAD signal indicates that the detected key-phrase is spoken by a wearer of the headphone. Responsive to determining that the VAD signal indicates that the detected key-phrase is spoken by the wearer of the headphone, triggering a virtual personal assistant (VPA).Type: GrantFiled: October 28, 2019Date of Patent: April 2, 2024Assignee: Apple Inc.Inventors: Sorin V. Dusan, Sungyub D. Yoo, Dubravko Biruski
-
Patent number: 11683632Abstract: An automatic speech recognition (ASR) triggering system, and a method of providing an ASR trigger signal, is described. The ASR triggering system can include a microphone to generate an acoustic signal representing an acoustic vibration and an accelerometer worn in an ear canal of a user to generate a non-acoustic signal representing a bone conduction vibration. A processor of the ASR triggering system can receive an acoustic trigger signal based on the acoustic signal and a non-acoustic trigger signal based on the non-acoustic signal, and combine the trigger signals to gate an ASR trigger signal. For example, the ASR trigger signal may be provided to an ASR server only when the trigger signals are simultaneously asserted. Other embodiments are also described and claimed.Type: GrantFiled: August 17, 2021Date of Patent: June 20, 2023Assignee: Apple Inc.Inventors: Sorin V. Dusan, Aram M. Lindahl, Robert D. Watson
-
Patent number: 11343605Abstract: System for automatic right-left ear detection for headphone comprising: first earcup and second earcup that are identical. Each of first and second earcups includes: first microphone located on perimeter of each earcup, when first earcup is worn on user's right ear first microphone of first earcup is at location farthest from user's mouth when headphone is worn in normal wear position; second microphone located on perimeter of each earcup, when first earcup is worn on user's right ear, second microphone of first earcup is at location closer than first microphone of first earcup to user's mouth; third microphone located inside each earcup facing user's ear cavity, fourth microphone located at perimeter and bottom center portion of each earcup and facing exterior of each earcup, and fifth microphone located on perimeter of each earcup above and to left of second microphone when looking at outside housing of each earcup.Type: GrantFiled: December 27, 2019Date of Patent: May 24, 2022Assignee: APPLE INC.Inventor: Sorin V. Dusan
-
Publication number: 20220151560Abstract: A wearable device that attaches to a body part of a user via an attachment member operates in at least a connected and a disconnected state. One or more sensors located in the wearable device and/or the attachment member detect the user's body part when present. Such detection may only be performed when the attachment member is in a connected configuration and may be used to switch the wearable device between the connected and disconnected states. In this way, the wearable device operates in the connected state when worn by a user and in the disconnected state when not worn by the user.Type: ApplicationFiled: February 4, 2022Publication date: May 19, 2022Inventors: Sorin V. Dusan, Daniel J. Culbert, Todd K. Whitehurst
-
Patent number: 11290599Abstract: A method performed by a near-end headphone device, while the device is engaged in a voice communication session with a far-end device. The method receives a downlink audio signal from the far-end device and drives a speaker with the downlink audio signal. The method receives an accelerometer signal from an accelerometer of the near-end device and performs echo cancellation and residual echo suppression. The method generates a combined SNR-RES signal based on a SNR of the echo cancelled the accelerometer signal and the residual echo suppression signal. The method determines whether the combined SNR-RES signal is below a threshold. In response to being below the threshold, the method gates the echo cancelled accelerometer signal, generates an uplink audio signal by blending the gated signal with a microphone signal and transmits the uplink audio signal to the far-end device.Type: GrantFiled: September 22, 2020Date of Patent: March 29, 2022Assignee: APPLE INC.Inventors: Sorin V. Dusan, Tony S. Verma
-
Patent number: 11281262Abstract: An electronic device that can be worn on a limb of a user can include a processing device and one or more position sensing devices operatively connected to the processing device. The processing device can be adapted to determine which limb of the user is wearing the electronic device based on one or more signals received from at least one position sensing device.Type: GrantFiled: July 24, 2020Date of Patent: March 22, 2022Assignee: Apple Inc.Inventor: Sorin V. Dusan
-
Publication number: 20220038819Abstract: Systems, methods, devices and non-transitory, computer-readable storage mediums are disclosed for location-tracking wireless devices. In an embodiment, a method performed by an electronic device comprises: playing, or initiating the playing of, a sound through a loudspeaker of an accessory device via a communication link. The sound is played at a specified frequency that utilizes a frequency response of the loudspeaker (or loudspeaker plus speaker enclosure). The sound is received through two or more microphones of the electronic device and filtered by one or more filters. The one or more filters are configured to pass the sound at or around the specified frequency and to reduce masking of the sound by ambient noise. The filtered sound is associated with direction data generated from sensor data provided by one or more inertial sensors of the electronic device. In another embodiment, the specified frequency is higher than the maximum human hearing range.Type: ApplicationFiled: June 11, 2021Publication date: February 3, 2022Inventors: Sorin V. Dusan, Raghunandan K. Pai, Scott Lopatin, Tommy Rochette, Navin Bindiganavile Suparna, Emmanuel Lalande, Siva Ganesh Movva, Robert Watson, Scott Grinker
-
Patent number: 11227617Abstract: A device implementing an automatic speech recognition triggering system includes at least one processor configured to receive first and second audio signals respectively corresponding to first and second microphones of a device. The at least one processor is further configured to generate, based on at least one of the first or second audio signals, a third audio signal corresponding to a voice beam directed to an expected position of a mouth of a user. The at least one processor is further configured to determine whether wind noise is present in at least one of the first, second, or third audio signals. The at least one processor is further configured to, based on determining whether wind noise is present, an audio signal from among the second or third audio signals, for a determination of whether at least one of the first or second audio signals corresponds to the user.Type: GrantFiled: September 6, 2019Date of Patent: January 18, 2022Assignee: Apple Inc.Inventors: Sorin V. Dusan, Sungyub D. Yoo, Dubravko Biruski
-
Publication number: 20210377650Abstract: An automatic speech recognition (ASR) triggering system, and a method of providing an ASR trigger signal, is described. The ASR triggering system can include a microphone to generate an acoustic signal representing an acoustic vibration and an accelerometer worn in an ear canal of a user to generate a non-acoustic signal representing a bone conduction vibration. A processor of the ASR triggering system can receive an acoustic trigger signal based on the acoustic signal and a non-acoustic trigger signal based on the non-acoustic signal, and combine the trigger signals to gate an ASR trigger signal. For example, the ASR trigger signal may be provided to an ASR server only when the trigger signals are simultaneously asserted. Other embodiments are also described and claimed.Type: ApplicationFiled: August 17, 2021Publication date: December 2, 2021Inventors: Sorin V. Dusan, Aram M. Lindahl, Robert D. Watson
-
Patent number: 11166104Abstract: An electronic device that can be worn by a user can include a processing unit and one or more sensors operatively connected to the processing unit. The processing unit can be adapted to determine an installation position of the electronic device based on one or more signals received from at least one sensor.Type: GrantFiled: September 23, 2020Date of Patent: November 2, 2021Assignee: Apple Inc.Inventor: Sorin V. Dusan
-
Patent number: 11102568Abstract: An automatic speech recognition (ASR) triggering system, and a method of providing an ASR trigger signal, is described. The ASR triggering system can include a microphone to generate an acoustic signal representing an acoustic vibration and an accelerometer worn in an ear canal of a user to generate a non-acoustic signal representing a bone conduction vibration. A processor of the ASR triggering system can receive an acoustic trigger signal based on the acoustic signal and a non-acoustic trigger signal based on the non-acoustic signal, and combine the trigger signals to gate an ASR trigger signal. For example, the ASR trigger signal may be provided to an ASR server only when the trigger signals are simultaneously asserted. Other embodiments are also described and claimed.Type: GrantFiled: April 26, 2019Date of Patent: August 24, 2021Assignee: APPLE INC.Inventors: Sorin V. Dusan, Aram M. Lindahl, Robert D. Watson
-
Patent number: 11051105Abstract: Systems, methods, devices and non-transitory, computer-readable storage mediums are disclosed for location-tracking wireless devices. In an embodiment, a method performed by an electronic device comprises: playing, or initiating the playing of, a sound through a loudspeaker of an accessory device via a communication link. The sound is played at a specified frequency that utilizes a frequency response of the loudspeaker (or loudspeaker plus speaker enclosure). The sound is received through two or more microphones of the electronic device and filtered by one or more filters. The one or more filters are configured to pass the sound at or around the specified frequency and to reduce masking of the sound by ambient noise. The filtered sound is associated with direction data generated from sensor data provided by one or more inertial sensors of the electronic device. In another embodiment, the specified frequency is higher than the maximum human hearing range.Type: GrantFiled: September 2, 2020Date of Patent: June 29, 2021Assignee: Apple Inc.Inventors: Sorin V. Dusan, Raghunandan K. Pai, Scott Lopatin, Tommy Rochette, Navin Bindiganavile Suparna, Emmanuel Lalande, Siva Ganesh Movva, Robert Watson, Scott Grinker
-
Publication number: 20210125609Abstract: A signal processing method to determine whether or not a detected key-phrase is spoken by a wearer of a headphone. The method receives an accelerometer signal from an accelerometer in a headphone and receives a microphone signal from at least one microphone in the headphone. The method detects a key-phrase using the microphone signal and generates a voice activity detection (VAD) signal based on the accelerometer signal. The method determines whether the VAD signal indicates that the detected key-phrase is spoken by a wearer of the headphone. Responsive to determining that the VAD signal indicates that the detected key-phrase is spoken by the wearer of the headphone, triggering a virtual personal assistant (VPA).Type: ApplicationFiled: October 28, 2019Publication date: April 29, 2021Inventors: Sorin V. Dusan, Sungyub D. Yoo, Dubravko Biruski
-
Publication number: 20210099782Abstract: An earphone has a housing and a corresponding user-contact surface configured to urge against a user's anatomy. The housing defines an acoustic chamber and an acoustic port opening from the acoustic chamber. The user-contact surface is complementarily configured relative to the user's anatomy. When the earphone is donned, the user-contact surface forms an acoustic seal between the user-contact surface and the user's anatomy, acoustically coupling the acoustic chamber with the user's ear canal. An acoustic driver is positioned in the housing and acoustically coupled with the acoustic chamber. A microphone transducer acoustically couples with the acoustic port. A processing component is configured to detect a presence or an absence of anti-resonance in a spectral envelope observed by the microphone transducer.Type: ApplicationFiled: August 20, 2020Publication date: April 1, 2021Inventors: Sorin V. Dusan, Dubravko Biruski, Sungyub D. Yoo
-
Publication number: 20210074309Abstract: A device implementing an automatic speech recognition triggering system includes at least one processor configured to receive first and second audio signals respectively corresponding to first and second microphones of a device. The at least one processor is further configured to generate, based on at least one of the first or second audio signals, a third audio signal corresponding to a voice beam directed to an expected position of a mouth of a user. The at least one processor is further configured to determine whether wind noise is present in at least one of the first, second, or third audio signals. The at least one processor is further configured to, based on determining whether wind noise is present, an audio signal from among the second or third audio signals, for a determination of whether at least one of the first or second audio signals corresponds to the user.Type: ApplicationFiled: September 6, 2019Publication date: March 11, 2021Inventors: Sorin V. DUSAN, Sungyub D. YOO, Dubravko BIRUSKI
-
Patent number: 10896682Abstract: A speaker recognition algorithm is trained (one or more of its models are tuned) with samples of a microphone signal produced by an inside microphone of a headphone, while the headphone is worn by a speaker. The trained speaker recognition algorithm then tests other samples of the inside microphone signal and produces multiple speaker identification scores for its given models, or a single speaker verification likelihood score for a single given model. Other embodiments are also described and claimed.Type: GrantFiled: October 23, 2018Date of Patent: January 19, 2021Assignee: APPLE INC.Inventor: Sorin V. Dusan
-
Publication number: 20210014617Abstract: An electronic device that can be worn by a user can include a processing unit and one or more sensors operatively connected to the processing unit. The processing unit can be adapted to determine an installation position of the electronic device based on one or more signals received from at least one sensor.Type: ApplicationFiled: September 23, 2020Publication date: January 14, 2021Inventor: Sorin V. Dusan
-
Publication number: 20200404423Abstract: Systems, methods, devices and non-transitory, computer-readable storage mediums are disclosed for location-tracking wireless devices. In an embodiment, a method performed by an electronic device comprises: playing, or initiating the playing of, a sound through a loudspeaker of an accessory device via a communication link. The sound is played at a specified frequency that utilizes a frequency response of the loudspeaker (or loudspeaker plus speaker enclosure). The sound is received through two or more microphones of the electronic device and filtered by one or more filters. The one or more filters are configured to pass the sound at or around the specified frequency and to reduce masking of the sound by ambient noise. The filtered sound is associated with direction data generated from sensor data provided by one or more inertial sensors of the electronic device. In another embodiment, the specified frequency is higher than the maximum human hearing range.Type: ApplicationFiled: September 2, 2020Publication date: December 24, 2020Inventors: Sorin V. Dusan, Raghunandan K. Pai, Scott Lopatin, Tommy Rochette, Navin Bindiganavile Suparna, Emmanuel Lalande, Siva Ganesh Movva, Robert Watson, Scott Grinker