Orchestrated Voice-Profile Audio Filtering on Heterogeneous Platforms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The transition from x86 to ARM-based processors in Information Handling Systems (IHSs) presents challenges in management, deployment, and configuration, particularly in filtering collaboration session audio effectively using voice profiles across heterogeneous computing platforms.
Innovation Solution
A heterogeneous computing platform with an orchestrator device that receives voice profiles and reduces noise in audio inputs by instructing Digital Signal Processors or AI devices to attenuate or exclude audio components that do not match the profile, using firmware services and policies without host OS involvement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If voice profile-based noise filtering is implemented in heterogeneous computing platforms, then audio quality in collaboration sessions is improved, but system complexity increases due to multiple devices and firmware services
Solution Approach 1:
The system segments audio processing functionality across multiple specialized devices (aDSP, AI device, sensor hub, EC, BMC) within the heterogeneous platform. Each device handles specific aspects of voice profile-based noise filtering through dedicated firmware services, allowing complex audio filtering to be divided into manageable, independent components that can operate in parallel
Solution Approach 2:
The orchestrator device serves as an intermediary that coordinates between the various firmware services and the host OS. It receives voice profiles, manages the collaboration session context, and directs audio processing tasks to appropriate firmware services, simplifying the overall system architecture by providing a centralized control point
2Productivity
If firmware services are used for audio processing without host OS involvement, then processing efficiency is improved, but ease of operation deteriorates due to direct device communication requirements
Solution Approach 1:
The orchestrator acts as an intermediary layer between the host OS and firmware services. It receives high-level requests from the host OS regarding collaboration sessions and voice profiles, then translates these into specific instructions for the appropriate firmware services (aDSP, AI device), maintaining ease of operation while enabling efficient direct hardware processing
Solution Approach 2:
Firmware services are designed to operate autonomously without requiring host OS involvement in audio processing tasks. Each firmware service (aDSP, AI device, sensor hub) independently executes its designated audio filtering functions based on parameters provided by the orchestrator, enabling self-service operation that improves processing efficiency
Data Source
AI summary
Systems and methods for filtering collaboration session audio using voice profiles in heterogenous computing platforms are described. In an illustrative, non-limiting embodiment, 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: receive a voice profile of a participant of a collaboration session and reduce noise in an audio input of the heterogeneous computing platform based on the voice profile during the collaboration session.