Voice assistant with sound metering capabilities

Patent metadata

Field	Value
Publication number	US-11776539-B2
Application number	US-201916731270-A
Country	US
Kind code	B2
Filing date	Dec 31, 2019
Priority date	Jan 8, 2019
Publication date	Oct 3, 2023
Grant date	Oct 3, 2023

Abstract

Described are systems and methods for enabling voice interaction with appliances, services (e.g., media streaming services, gaming services, news feed services, social platform services, etc.), and the like by way of appropriate supplied apps (also referred to as “skills,” “actions,” or the like) which may be presented or downloaded to a smart device having associated therewith one or more cloud-based voice service platforms. Also described are systems that utilize one or more microphones to provide sound metering for control purposes.

First claim

What is claimed is:

1. A non-transitory, computer readable media having stored thereon instructions executable by a processing device associated with a sound metering device, the instructions, when executed by the processing device, causing the sound metering device to perform steps, comprising:
while at least one controllable device is operating in a one of a plurality of operating states within an environment, calculating a signature for a first sound captured within the environment via use of a one or more microphones associated with the sound metering device;
causing the calculated signature for the first sound to be stored in a data repository in association with the one of the plurality of operating states of the at least one controllable device;
responding to an input that is received by the sound metering device and that is associated with a desired state of the at least one controllable appliance by using the input and the calculated signature for the first sound as retrieved from the data repository to predict an event to dispatch to a controlling application adapted to cause commands for controlling corresponding functional operations of the at least one controllable appliance to be communicated to the at least one controllable appliance;
dispatching the predicted event to the controlling application whereupon the controlling application will use the dispatched, predicted event to cause one or more commands to be communicated to the at least one controllable appliance to thereby place the at least one controllable appliance into the desired state.

2. The computer-readable media as recited in claim 1 , wherein the controlling application and the sound metering device are component parts of a controlling device.

3. The computer-readable media as recited in claim 1 , wherein the controlling application comprises a skill associated with the at least one controllable appliance installed on a device in communication with the sound metering device.

4. The computer-readable media as recited in claim 1 , wherein the at least one controllable appliance comprises a component of at least one of a heating system and a cooling system.

5. The computer-readable media as recited in claim 1 , wherein the at least one controllable appliance comprises a component of a home security system.

6. The computer-readable media as recited in claim 1 , wherein the at least one controllable appliance comprises a component of an audio/visual entertainment system.

7. The computer-readable media as recited in claim 1 , wherein the input comprises a voice command received via the one or more microphones.

8. The computer-readable media as recited in claim 1 , wherein the desired state of the at least one controllable appliance comprises a volume state.

9. The computer-readable media as recited in claim 1 , wherein the instructions cause the sound meter to suppress background noise when calculating the signature for the first sound captured within the environment.

10. The computer-readable media as recited in claim 1 , wherein the instructions cause the sound meter to use a direction associated with first sound when calculating the signature for the first sound captured within the environment.

11. The computer-readable media as recited in claim 1 , wherein the instructions cause the sound meter to calculate a signature for a second sound captured within the environment via use of the one or more microphones associated with the sound metering device, cause the calculated signature for the second sound to be stored in the data repository, and respond to the input by using the input, the calculated signature for the second sound as retrieved from the data repository, and the calculated signature for the first sound as retrieved from the data repository to predict the event to dispatch to the controlling application.

12. The computer-readable media as recited in claim 11 , wherein the first sound comprises a sound captured while an audio generating appliance within the environment is operating at a minimal volume level and the second sound comprises a further sound captured while the audio generating appliance within the environment is operating at a maximum volume level.

13. The computer-readable media as recited in claim 1 , wherein the instructions cause the sound meter to respond to the input by using the input, a current state of the at least one controllable appliance, and the calculated signature for the first sound as retrieved from the data repository to predict the event to dispatch to the controlling application.

14. The computer-readable media as recited in claim 13 , wherein the instructions cause the sound meter to use input received via use of the one or more microphones to determine the current state of the at least one controllable appliance.

15. The computer-readable media as recited in claim 1 , wherein the desired state comprises a media access state for the at least one controllable appliance.

16. The computer-readable media as recited in claim 15 , wherein the media access state comprises a channel tuning state for the at least one controllable appliance and wherein the first sound captured within the environment comprises a sound being output by the at least one controllable appliance while in the channel tuning state.

17. The computer-readable media as recited in claim 12 , wherein the instructions cause the sound metering device to determine an amount of time required to transition the audio generating appliance from the maximum volume level to the minimal volume level and wherein the input, the determined amount of time, and the calculated signature for the first sound as retrieved from the data repository is used to predict the event to be dispatched to the controlling application.

Assignees

• Universal Electronics Inc

Inventors

• Hatambeiki Arsham
• Huang Haiming
• Ahmadi Nicu
• Yuh Allen
• Chen Jason
• Chambers Christopher
• Owrang Maryam

Classifications

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L25/51

  for comparison or discrimination · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title