Wake-on-voice Buffer Quality Management via Boot Profiling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Information Handling Systems (IHS) with wake-on-voice capabilities face challenges in managing buffer quality due to varying boot/wake times, leading to incomplete capture of audio commands when transitioning from sleep to active power states, as conventional approaches focus on adjusting buffer size rather than audio quality.
Innovation Solution
The system determines the expected time duration of future wake events based on historical profiling, adjusts audio signal quality by changing codec, compression, sample rate, bit depth, or number of channels to fit within a fixed-size buffer, ensuring complete capture of verbal commands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the buffer size is increased to capture complete audio commands during wake events, then the audio capture completeness is improved, but the memory usage and system resource consumption increase
Solution Approach 1:
The patent changes the parameters of the audio signal itself (quality, sample rate, bit depth, compression) rather than changing the buffer size. By adjusting these audio parameters dynamically based on predicted wake duration, the system fits variable-duration audio into a fixed-size buffer, resolving the contradiction between capture completeness and memory usage.
Solution Approach 2:
The system dynamically adjusts audio quality parameters based on predicted wake event duration. The audio encoder dynamically changes compression levels, sample rates, and bit depths to match the expected audio duration, allowing the fixed buffer to accommodate varying wake times without wasting memory resources.
2Measurement precision
If the audio quality is maintained at high levels during wake events, then the voice command processing accuracy is improved, but the buffer capacity is exceeded when wake times are long
Solution Approach 1:
The patent dynamically changes audio quality parameters (sample rate, bit depth, compression ratio) based on the predicted wake duration. When wake time is short, high quality settings are used to maintain accuracy. When wake time is long, quality is reduced to fit the fixed buffer, thus resolving the contradiction between accuracy and buffer capacity.
Solution Approach 2:
The system applies partial action by adjusting audio quality to the minimum necessary level required to capture the voice command accurately within the available buffer space. Rather than always using maximum quality, the system uses just enough quality to ensure accurate voice recognition, freeing up buffer space for longer wake events.
3Device complexity
If the buffer size is kept fixed to simplify memory management, then the system complexity is reduced, but the ability to accommodate variable wake times is limited
Solution Approach 1:
Instead of changing the fixed buffer size, the patent changes the audio encoding parameters (quality, compression, sample rate) to adapt to variable wake times. This maintains the simplicity of fixed buffer memory management while achieving adaptability through dynamic audio parameter adjustment.
Solution Approach 2:
The patent replaces the mechanical approach of variable buffer size allocation with a software-based audio encoding approach. Rather than physically expanding memory buffers, the system uses software audio compression and quality adjustment to achieve the same adaptive capability, reducing hardware complexity.
Data Source
AI summary
Systems and methods for managing wake-on-voice buffer quality based on system boot profiling. In an illustrative, non-limiting embodiment, an Information Handling System (IHS) may include at least one logic circuit and at least one memory circuit coupled to the at least one logic circuit, the at least one memory including program instructions stored thereon that, upon execution by the at least one logic circuit, cause the IHS to: determine an expected time duration of a future wake event; receive a verbal command from a user, the verbal command configured to trigger the future wake event; capture the verbal command as an audio signal; adjust at least one of: a quality of the audio signal or a duration of the audio signal, where the adjustment is based, at least in part, upon the expected time duration; and store the adjusted audio signal in a fixed-size buffer.