Seat-embedded speech sensors

Patent metadata

Field	Value
Publication number	US-12233752-B2
Application number	US-202117399950-A
Country	US
Kind code	B2
Filing date	Aug 11, 2021
Priority date	Aug 11, 2021
Publication date	Feb 25, 2025
Grant date	Feb 25, 2025

Abstract

Embodiments of the present disclosure a computer-implemented method comprising receiving sensor data from one or more vibration sensors that are embedded within a seat, where the sensor data includes data associated with speech by an occupant of the seat, and at least one of processing, transmitting, or storing the sensor data based on the data associated with the speech.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving vibration data from one or more vibration sensors that are embedded within a seat, wherein:
the seat includes a cushion with a side of the cushion comprising a cavity, the side being configured to face a user,
the one or more vibration sensors are disposed within the cavity, and
the first sensor data includes data associated with speech by an occupant of the seat; and

based on the data associated with the speech, at least one of:
processing, by a speech recognition algorithm, the vibration data to translate the vibration data into text, or
transmitting the vibration data to another device for playback as sound.

2. The computer-implemented method of claim 1 , wherein the first sensor data is processed by filtering out sensor data associated with frequencies that are below a predefined frequency.

3. The computer-implemented method of claim 1 , wherein the first sensor data is processed by filtering out sensor data associated with frequencies that are above a predefined frequency.

4. The computer-implemented method of claim 1 , further comprising combining the first sensor data with second sensor data from one or more acoustic microphones.

5. The computer-implemented method of claim 4 , further comprising determining whether to combine the first sensor data with the second sensor data based on frequencies indicated by at least one of the first sensor data or the second sensor data.

6. The computer-implemented method of claim 4 , wherein the first sensor data is combined with the second sensor data based on a level of signal output by the one or more vibration sensors and the one or more acoustic microphones.

7. The computer-implemented method of claim 4 , further comprising determining whether an amount of low-frequency energy indicated by the second sensor data is less than a threshold.

8. The computer-implemented method of claim 1 , further comprising receiving a signal from a pressure sensor or a contact switch, wherein the signal indicates that a user is in physical contact with at least one of the one or more vibration sensors.

9. The computer-implemented method of claim 1 , further comprising processing the first sensor data using at least one of a machine learning technique or a voice reconstruction technique.

10. A seat, comprising:
a cushion, wherein a side of the cushion comprises a cavity, the side being configured to face a user; and
a vibration sensor that is disposed within the cavity, wherein:
the vibration sensor acquires vibration data that includes data associated with speech by an occupant of the seat, and
the vibration data is at least one of:
(i) processed by a speech recognition algorithm to translate the vibration data into text, or
(ii) transmitted to another device for playback as sound.

11. The seat of claim 10 , further comprising a cover that covers the cushion and the vibration sensor.

12. The seat of claim 10 , wherein the vibration sensor senses at least one of acceleration, velocity, displacement, stress, or strain.

13. The seat of claim 10 , wherein the cushion comprises a seatback cushion, and a side of the vibration sensor protrudes from the seatback cushion.

14. The seat of claim 10 , wherein the side of the cushion comprises at least one other cavity, and the seat further comprises at least one other vibration sensor disposed within the at least one other cavity.

15. The seat of claim 10 , wherein the vibration sensor and a printed circuit board assembly are disposed within a housing, and the housing is disposed within the cavity.

16. The seat of claim 15 , wherein at least one of a pressure sensor or a contact switch is also disposed within the housing.

17. The seat of claim 10 , wherein the vibration sensor is configured to sense vibration frequencies up to at least 3 kHz.

18. The seat of claim 10 , wherein the seat is disposed within a vehicle.

19. The seat of claim 10 , wherein:
sensor data is acquired by one or more acoustic microphones;
when an amount of low frequency energy in the sensor data is less than a threshold, the vibration data is combined with the sensor data to produce combined data; and
the combined data is at least one of:
(i) processed by a speech recognition algorithm to translate the vibration data into text, or
(ii) transmitted to the another device for playback as sound.

20. One or more computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to perform steps of:
receiving vibration data from one or more vibration sensors that are embedded within a seat, wherein:
the seat includes a cushion with a side of the cushion comprising a cavity, the side being configured to face a user,
the one or more vibration sensors are disposed within the cavity, and
the vibration data includes data associated with speech by an occupant of the seat; and

based on the data associated with the speech, at least one of:
processing, by a speech recognition algorithm, the vibration data to translate the vibration data into text, or
transmitting the vibration data to another device for playback as sound.

Assignees

• Harman Int Ind

Inventors

• Du Yu

Classifications

• G10L25/78

  Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10) · CPC title

• H04R2499/13

  Acoustic transducers and sound field adaptation in vehicles · CPC title

• H04R2410/07

  Mechanical or electrical reduction of wind noise generated by wind passing a microphone · CPC title

• H04R3/04

  for correcting frequency response · CPC title

• H04R1/08

  Mouthpieces; {Microphones;} Attachments therefor · CPC title