IP Library Granted Patent US 12673585
Granted Patent B2
US 12673585 · App. 18/062,128 · Granted Jul 7, 2026

Vibration sensing steering wheel to optimize voice command accuracy

Inventors: Benjamin Piya Austin (Saline, MI); George M. Evans (Ann Arbor, MI); Philip J. Babian (Canton, MI)
Assignees: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.; TOYOTA JIDOSHA KABUSHIKI KAISHA
B60N2/0224B60H1/00757B60R16/0373G10L17/22E05F15/70E05Y2400/45E05Y2400/85E05Y2900/55
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12673585
App. No.
18/062,128
Granted
Jul 7, 2026
Kind
B2
Abstract

A system and method employ vibration sensors on board a vehicle to effectively identify and implement voice commands. The vibration sensors provide vibration signals corresponding to the speech of vehicle occupants to a controller. The controller may verify the content of the voice commands and identify a speaker of the voice commands with the vibration signals. The voice command may be implemented by operating a controlled device in a specific passenger zone of the vehicle. In some implementations, the speech of a specific occupant may be designated as voice commands to be transmitted over a videoconference or voice call and the speech of surrounding vehicle occupants may be designated as noise to be excluded from transmission. Further, driver voice commands may be given priority when conflicting commands are given by other vehicle passengers.

Claims (47)

1 . A voice recognition system for operating a controlled device on board a vehicle, the system comprising:

a microphone;

at least one vibration sensor disposed in an interior of the vehicle;

one or more processors; and

a computer readable medium storing instructions thereon that cause the one or more processors to:

receive audio signal data from the microphone;

receive vibration signals from the one or more vibration sensors;

detect a voice command from the audio signal data;

match the voice command to a vibration sensor signature detected within the vibration signals; and

operate a controlled device in response to matching the voice command to the vibration sensor signature,

wherein the instructions further cause the one or more processors to update a match criteria for matching the voice command to the vibration sensor signature in response to detection of clothing articles on an occupant of the vehicle, wherein reliance on the vibration sensor signature is reduced.

2 . The system as defined in claim 1 , wherein the at least one vibration sensor is associated with one of a plurality of passenger zones defined within the interior of the vehicle, and wherein the instructions further cause the one or more processors to operate the controlled device within the one of the plurality of passenger zones.

3 . The system as defined in claim 2 , wherein the controlled device comprises an adjustable seat or window.

4 . The system as defined in claim 2 , wherein the instructions further cause the one or more processors to instruct the controlled device to transmit speech of an occupant of the one of the plurality of passenger zones and prohibit transmission of the speech of an occupant of a surrounding passenger zone.

5 . The system as defined in claim 1 , wherein the at least one vibration sensor includes at least a first vibration sensor supported on a steering wheel of the vehicle.

6 . The system as defined in claim 5 , wherein the at least one vibration sensor includes at least a second vibration sensor supported in a foot pedal of the vehicle.

7 . The system as defined in claim 1 , wherein the instructions further cause the one or more processors to implement a machine learning model to update the match criteria.

8 . The system as defined in claim 1 , wherein the instructions further cause the one or more processors to:

detect conflicting voice commands from a driver of the vehicle and another occupant of the vehicle; and

in response to the detection of conflicting voice commands, giving priority to the driver of the vehicle.

9 . A computer-implemented method for operating a controlled device on board a vehicle, the method comprising:

receiving audio signal data from a microphone disposed in an interior of the vehicle;

receiving vibration signals from one or more vibration sensors disposed within the interior of the vehicle;

detecting a voice command from the audio signal with a voice recognition routine;

matching the voice command to a vibration sensor signature within the vibration signals data using at least one processor;

operating a controlled device in response to matching the voice command to the vibration sensor signature; and

updating a match criteria for matching the voice command to the vibration sensor signature in response to detection of clothing articles on an occupant of the vehicle, wherein reliance on the vibration sensor signature is reduced.

10 . The computer-implemented method as defined in claim 9 , further comprising identifying an occupant issuing the voice command with the vibration signals.

11 . The computer-implemented method as defined in claim 10 , wherein operating the controlled device is implemented within one of a plurality of passenger zones in which the occupant is located.

12 . The computer-implemented method as defined in claim 11 , further comprising instructing the controlled device to transmit speech of the occupant issuing the voice command and prohibit transmission of speech of occupants located in surrounding passenger zones.

13 . The computer-implemented method as defined in claim 9 , further comprising:

detecting a corrective action undertaken in response to operating the controlled device; and

updating a match criteria for matching the voice command to the vibration sensor signature in response to detecting the corrective action.

14 . The computer-implemented method as defined in claim 9 , wherein the controlled device is an adjustable seat or a window.

15 . The computer-implemented method as defined in claim 9 , wherein a voice command of a driver is given priority over a voice command of other vehicle passengers.

16 . A non-transitory computer-readable medium having machine-readable instructions stored thereon, which are executable to cause a machine to perform operations comprising:

receiving audio signal data from a microphone disposed in an interior of the vehicle;

receiving vibration signals from one or more vibration sensors disposed within the interior of a vehicle;

detecting a voice command from the audio signal with a voice recognition routine;

matching the voice command to a vibration sensor signature within the vibration signals data with at least one processor;

instructing a controlled device to operate in response to matching the voice command to the vibration sensor signature, wherein the controlled device comprises an adjustable seat or window; and

updating a match criteria for matching the voice command to the vibration sensor signature in response to detection of clothing articles on an occupant of the vehicle, wherein reliance on the vibration sensor signature is reduced.

17 . The non-transitory computer-readable medium as defined in claim 16 , wherein the machine-readable instructions are further executable to cause the machine to identify an occupant issuing the voice command with the vibration signals.

18 . The non-transitory computer-readable medium as defined in claim 16 , wherein the machine-readable instructions are further executable to instruct the controlled device to transmit speech of an occupant issuing the voice command and prohibit transmission of speech of surrounding occupants.

19 . The non-transitory computer-readable medium as defined in claim 16 , wherein the machine-readable instructions are further executable to:

detect a corrective action undertaken in response to operating the controlled device; and

update a match criteria for matching the voice command to the vibration sensor signature in response to detecting the corrective action.