Back to results
US 2023/0144825 A1Published application
Detecting input gestures using onboard microphones
AssigneeGoogle Inc.
InventorsJingying Hu, Juston Payne, Dongeek Shin, Shiblee Hasan, Xiuxiu Yuan
Life of this patent
Estimating the term…
Abstract
A method including generating two or more audio signals (e.g., by two or more microphones) based on a user interaction with a wearable device, generating an audio signature based on the two or more audio signals, and identifying at least one of a coordinate or a gesture based on an output of a machine-learned model given the audio signature.
Claims20
A wearable device comprising:
- two or more microphones configured to generate two or more audio signals based on a user interaction with the wearable device;
- a processor;
- and
- a memory storing instructions that cause the processor to:
- generate an audio signature based on the two or more audio signals, and
- identify at least one of a coordinate or a gesture based on an output of a machine-learned model given the audio signature.
3 more elements
A method comprising:
- generating two or more audio signals based on a user interaction with a wearable device including two or more microphones;
- generating an audio signature based on the two or more audio signals;
- and
- identifying at least one of a coordinate or a gesture based on an output of a machine-learned model given the audio signature.
1 more element
A non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, are configured to cause the processor to:
- receive two or more audio signals based on a user interaction with a wearable device using two or more microphones;
- generate an audio signature based on the two or more audio signals;
- and
- identify at least one of a coordinate or a gesture based on an output of a machine-learned model given the audio signature.
1 more element
Dependencies are inferred from the claim text.