Contextual noise suppression and acoustic context awareness (ACA) during a collaboration session in a heterogenous computing platform

Patent metadata

Field	Value
Publication number	US-12561278-B2
Application number	US-202217821826-A
Country	US
Kind code	B2
Filing date	Aug 24, 2022
Priority date	Aug 24, 2022
Publication date	Feb 24, 2026
Grant date	Feb 24, 2026

Abstract

Systems and methods for contextual noise suppression and Acoustic Context Awareness (ACA) during a collaboration session in a heterogenous computing platform are described. In some embodiments, an Information Handling System (IHS) may include: a heterogeneous computing platform comprising a plurality of devices and a memory coupled to the heterogeneous computing platform, where the memory comprises a plurality of sets of firmware instructions, where each set of firmware instructions, upon execution by a respective device, enables the respective device to provide a corresponding firmware service, and where at least one of the plurality of devices operates as an orchestrator configured to: detect a location of the IHS during a collaboration session and, in response to the detection, change a noise suppression setting.

First claim

The invention claimed is:

1 . An Information Handling System (IHS), comprising:
a heterogeneous computing platform comprising a plurality of devices; and a memory coupled to the heterogeneous computing platform, wherein the memory comprises a plurality of sets of firmware instructions, wherein each set of firmware instructions, upon execution by a respective device of the plurality of devices, enables the respective device to provide a corresponding firmware service, and wherein an application executed on the IHS operates as an orchestrator configured to:
detect a location of the IHS during a collaboration session;
in response to the detection, change a noise suppression setting to a modified noise suppression setting;
determine a battery-charge state of the IHS and a level of utilization of a high-performance Artificial Intelligence (AI) device of the heterogeneous computing platform;
select, based at least in part, on a received policy encoded as a markup language or JavaScript Object Notation (JSON), one of: the high-performance AI device, or a sensor hub low-power AI device, wherein the high-performance AI device is selected when the battery-charge state exceeds a first threshold and the level of utilization of the high-performance AI device is below a second threshold, and wherein the sensor hub low-power AI device is selected otherwise; and
identify, and suppress from transmission to at least one participant, at least one noise detected while the collaboration session is active, based, at least in part, on the selected device and the modified noise suppression setting.

2 . The IHS of claim 1 , wherein the heterogeneous computing platform comprises: a System-On-Chip (SoC), a Field-Programmable Gate Array (FPGA), or an Application-Specific Integrated Circuit (ASIC).

3 . The IHS of claim 1 , wherein the orchestrator comprises a sensing hub.

4 . The IHS of claim 1 , wherein the orchestrator comprises an Embedded Controller (EC) or a Baseboard Management Controller (BMC).

5 . The IHS of claim 1 , wherein the collaboration session comprises an audio or a video conference.

6 . The IHS of claim 1 , wherein the orchestrator is configured to receive a message or an instruction from an Operating System (OS) agent or application that indicates a start of the collaboration session.

7 . The IHS of claim 1 , wherein to change the noise suppression setting, the orchestrator is configured to receive a message from an Operating System (OS) agent or an application to implement a policy received from an Information Technology Decision Maker (ITDM) or Original Equipment Manufacturer (OEM).

8 . The IHS of claim 7 , wherein the policy identifies a rule that associates the location with the change to the noise suppression setting.

9 . The IHS of claim 7 , wherein to change the noise suppression setting, the orchestrator is configured to send a message to a firmware service provided by an audio Digital Signal Processor (aDSP) among the plurality of devices via an Application Programming Interface (API) without any involvement by any host Operating System (OS) to turn noise suppression on or off.

10 . The IHS of claim 9 , wherein the firmware service is configured to indicate the noise suppression setting to the host OS, at least in part, as a Human Interface Device (HID) report.

11 . The IHS of claim 7 , wherein to change the noise suppression setting, the orchestrator is configured to send a message to a firmware service provided by the high-performance AI device, the sensor hub low-power AI device, or an audio Digital Signal Processor (aDSP) among the plurality of devices via an Application Programming Interface (API) without any involvement by any host Operating System (OS) to execute a noise suppression AI model.

12 . The IHS of claim 11 , wherein the noise suppression AI model is selected based upon contextual information.

13 . The IHS of claim 1 , wherein the orchestrator is further configured to, in response to the detection, change an Acoustic Context Awareness (ACA) setting.

14 . The IHS of claim 13 , wherein to change the ACA setting, the orchestrator is configured to send a message to a firmware service provided by the high-performance AI device, the sensor hub low-power AI device, or an audio Digital Signal Processor (aDSP) among the plurality of devices via an Application Programming Interface (API) without any involvement by any host Operating System (OS) to execute an AI model.

15 . The IHS of claim 14 , wherein the AI model is selected based upon contextual information.

16 . The IHS of claim 1 , wherein the sets of firmware instructions are delivered to the plurality of devices as one or more extension drivers within a firmware installation package prior to the collaboration session.

17 . A memory coupled to a heterogeneous computing platform, wherein the heterogeneous computing platform comprises a plurality of devices, wherein the memory is configured to receive a plurality of sets of firmware instructions, wherein each set of firmware instructions, upon execution by a respective device of the plurality of devices, enables the respective device to provide a corresponding firmware service without any involvement by any host Operating System (OS), and wherein an application executed on the heterogeneous computing platform operates as an orchestrator configured to:
receive a policy encoded as a markup language or JavaScript Object Notation (JSON); detect a location of the heterogeneous computing platform during a collaboration session; in response to the detection, change an Acoustic Context Awareness (ACA) setting to a modified ACA setting; determine a battery-charge state associated with the heterogeneous computing platform and a level of utilization of a high-performance Artificial Intelligence (AI) device of the heterogeneous computing platform; select, based at least in part, on the received policy, one of: the high-performance AI device, or an always-on sensor hub low-power AI device, wherein the high-performance AI device is selected when the battery-charge state exceeds a first threshold and the level of utilization of the high-performance AI device is below a second threshold, and wherein the sensor hub low-power AI device is selected otherwise; and identify, and suppress from transmission to at least one participant, at least one noise detected while the collaboration session is active, based, at least in part, on the selected device and the modified ACA setting.

18 . The memory of claim 17 , wherein to detect the location of the heterogeneous computing platform, the orchestrator is configured to receive location data from one or more firmware services provided by one or more of the plurality of devices via an Application Programming Interface (API), and wherein the location data comprises Global Positioning System (GPS) data or wireless network data.

19 . A method, comprising:
receiving a firmware installation package comprising extension drivers in a heterogeneous computing platform comprising a plurality of devices, wherein upon execution, each extension driver causes a respective device of the plurality of devices to provide a firmware service to other devices via an Application Programming Interface (API); delivering an indication of a policy encoded as a markup language or JavaScript Object Notation (JSON) to an application executed on the heterogeneous computing platform, wherein the application is operating as an orchestrator, and wherein the policy is usable by the orchestrator to c

Assignees

• Dell Products Lp

Inventors

• Hamlin Daniel L
• Kondapi Srikanth
• Swierk Todd Erick

Classifications

• G06F9/44505

  Configuring for program initiating, e.g. using registry, configuration files · CPC title

• G06F15/7871 Primary

  Reconfiguration support, e.g. configuration loading, configuration switching, or hardware OS · CPC title

• G10L21/0208 Primary

  Noise filtering · CPC title