Back to results
US 11,908,479 B2Granted
Virtual assistant identification of nearby computing devices
AssigneeGoogle Inc.
InventorJian Wei Leong
Life of this patent
Estimating the term…
Abstract
In one example, a method includes method comprising: receiving audio data generated by a microphone of a current computing device; identifying, based on the audio data, one or more computing devices that each emitted a respective audio signal in response to speech reception being activated at the current computing device; and selecting either the current computing device or a particular computing device from the identified one or more computing devices to satisfy a spoken utterance determined based on the audio data.
Claims21
A battery powered device comprising:
- one or more microphones,
- one or more Wi-Fi network interfaces;
- one or more processors;
- and
- memory storing instructions that, when executed, cause one or more of the processors to:
- recognize speaking of a predetermined phrase in audio data received via one or more of the microphones;
- in response to recognizing the speaking of the predetermined phrase:
- transmit a request that:
- causes a second computing device, that is located in a physical environment with the battery powered device, to emit a second device audio signal via a second device speaker component of the second computing device, and
- causes a third computing device, that is also located in the physical environment, to emit a third device audio signal via a third device speaker component of the third computing device,
- wherein the second device audio signal and the third device audio signal are each above a range of human hearing;
- detect, at the battery powered device and via one or more of the microphones of the battery powered device, the second device audio signal and the third device audio signal;
- determine, based on at least (i) the second device audio signal as detected at the battery powered device and (ii) the third device audio signal as detected at the battery powered device, that the second computing device is most proximal to the battery powered device;
- and
- in response to determining that the second computing device is most proximal to the battery powered device:
- cause the second computing device to provide audible output.
13 more elements
A battery powered device comprising:
- one or more microphones,
- one or more Wi-Fi network interfaces;
- one or more processors;
- and
- memory storing instructions that, when executed, cause one or more of the processors to:
- recognize speaking of a predetermined phrase in audio data received via one or more of the microphones;
- and
- in response to recognizing the speaking of the predetermined phrase:
- transmit, by the battery powered device:
- a second device request that causes a second computing device, that is located in a physical environment with the battery powered device, to emit a second device audio signal via a second device speaker component of the second computing device, and
- a third device request that causes a third computing device, that is also located in the physical environment, to emit a third device audio signal via a third device speaker component of the third computing device,
- wherein the second device audio signal and the third device audio signal are each above a range of human hearing;
- and
- subsequent to transmitting the second device request and the third device request:
- acoustically detect, at the battery powered device and via one or more of the microphones of the battery powered device, the second device audio signal emitted by the second computing device and the third device audio signal emitted by the third computing device;
- determine, based on at least (i) the second device audio signal as detected at the battery powered device and (ii) the third device audio signal as detected at the battery powered device, that the second computing device is most proximal to the battery powered device;
- and
- in response to determining that the second computing device is most proximal to the battery powered device:
- cause the second computing device to provide audible output.
16 more elements
A method implemented by one or more processors of a first computing device, the method comprising:
- recognizing speaking of a predetermined phrase in audio data received via one or more microphones of the first computing device;
- in response to recognizing the speaking of the predetermined phrase:
- transmitting a request that:
- causes a second computing device, that is located in a physical environment with the first computing device, to emit a second device audio signal via a second device speaker component of the second computing device, and
- causes a third computing device, that is also located in the physical environment, to emit a third device audio signal via a third device speaker component of the third computing device,
- wherein the second device audio signal and the third device audio signal are each above a range of human hearing;
- detecting, via one or more of the microphones of the battery powered device, the second device audio signal and the third device audio signal;
- determining, based on at least (i) the second device audio signal as detected via one or more of the microphones and (ii) the third device audio signal as detected via one or more of the microphones, that the second computing device is most proximal to the first computing device;
- and
- in response to determining that the second computing device is most proximal to the first computing device:
- cause the second computing device to provide audible output.
8 more elements
Dependencies are inferred from the claim text.