US2022108700A1PendingUtilityA1
Personalized Talking Detector For Electronic Device
Est. expiryApr 23, 2039(~12.7 yrs left)· nominal 20-yr term from priority
Inventors:Jae-Hoon Lee
H04M 1/72454H04M 1/6066G06F 3/167H04R 29/004H04M 2250/74G10L 17/00
55
PatentIndex Score
0
Cited by
0
References
0
Claims
Abstract
The present disclosure provides for improved hot word detection in electronic devices, particularly small form factor devices such as wearables. The electronic device includes an accelerometer onboard to pick up voice in noisy conditions, and utilizes the accelerometer to confirm that a particular user intended to activate the hot word detection, thereby reducing false detection of other people's voices.
Claims
exact text as granted — not AI-modified1 . A method for detecting, by an electronic device, whether a specific user is speaking, the method comprising:
receiving, by one or more processors, an accelerometer signal from an accelerometer; determining that the accelerometer signal exceeds a predetermined threshold; receiving, by the one or more processors, a voice signal from a microphone; and determining, by using a comparison of the voice signal with the accelerometer signal, whether the specific user is talking.
2 . The method of claim 1 , wherein the electronic device is a wearable device, and the specific user is wearing the electronic device.
3 . The method of claim 2 , wherein the electronic device is a head-mounted device.
4 . The method of claim 3 , wherein the head-mounted device comprises one of: earbuds, a headset, or smart glasses.
5 . The method of claim 1 , further comprising activating the microphone in response to receiving the accelerometer signal.
6 . The method of claim 1 , further comprising listening, by the one or more processors through the microphone, for commands when the specific user is talking.
7 . The method of claim 1 , wherein the predetermined threshold indicates user activity consistent with talking and is dependent on a type of the electronic device.
8 . The method of claim 1 , further comprising updating the predetermined threshold based on historical accelerometer signals from the specific user.
9 . An electronic device, comprising:
an accelerometer; a microphone; and one or more processors in communication with the accelerometer and the microphone, the one or more processors configured to:
receive an accelerometer signal from the accelerometer;
determine that the accelerometer signal exceeds a predetermined threshold;
receive a voice signal from the microphone; and
determine, by using a comparison of the voice signal with the accelerometer signal, whether a specific user is talking.
10 . The electronic device of claim 9 , wherein the electronic device is a wearable device, and the specific user is wearing the electronic device.
11 . The electronic device of claim 10 , wherein the electronic device is a head-mounted device.
12 . The electronic device of claim 11 , wherein the head-mounted device comprises one of: earbuds, a headset, or smart glasses.
13 . The electronic device of claim 9 , wherein the one or more processors are further configured to activate the microphone in response to receiving the accelerometer signal.
14 . The electronic device of claim 9 , wherein the one or more processors are further configured to listen, through the microphone, for commands when the specific user is talking.
15 . The electronic device of claim 9 , wherein the predetermined threshold indicates user activity consistent with talking and is dependent on a type of the electronic device.
16 . The electronic device of claim 9 , wherein the one or more processors are further configured to update the predetermined threshold based on historical accelerometer signals from the specific user.
17 . A non-transitory computer-readable medium storing instructions executable by one or more processors for performing a method of detecting whether a specific user is speaking, the method comprising:
receiving an accelerometer signal; determine that the accelerometer signal exceeds a predetermined threshold; receiving a voice signal; and determining, by using a comparison of the voice signal with the accelerometer signal, whether the specific user is talking.
18 . The non-transitory computer-readable medium of claim 17 , wherein the method further comprises activating a microphone in response to receiving the accelerometer signal.
19 . The non-transitory computer-readable medium of claim 17 , wherein the method further comprises listening for commands when the specific user is talking.
20 . The non-transitory computer-readable medium of claim 17 , wherein the predetermined threshold indicates user activity consistent with talking and is dependent on a type of an electronic device by which the accelerometer signal is received.Join the waitlist — get patent alerts
Track US2022108700A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.