Low-Power Engine Voice Wake and Speaker Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern computing devices require physical interaction and additional authentication steps to wake up from a low-power state and access user data, which is inconvenient and inefficient in terms of power consumption.
Innovation Solution
Implementing a low-power engine that recognizes wake phrases and performs speaker verification using the same audio input, allowing devices to transition from a low-power state to an active state and authenticate users hands-free and eyes-free, reducing the need for additional input methods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If the device enters a low-power state to preserve power, then power consumption is reduced, but the device requires additional physical interaction and authentication steps to wake up
Solution Approach 1:
The system performs preliminary speaker verification using audio input captured while the device is in low-power state. The low-power engine processes the audio to verify the speaker's identity before fully waking the device, so that authentication is already completed when the device transitions to active state
Solution Approach 2:
The patent replaces mechanical/physical interaction (button pressing, touchscreen unlocking) with acoustic field interaction (voice-based speaker verification). The low-power engine uses audio signal processing to verify speaker identity without requiring physical user interaction to wake the device
2Reliability
If the device requires additional authentication steps to verify users, then security is improved, but the number of interaction steps increases
Solution Approach 1:
The patent merges the wake-up process and authentication process into a single integrated operation. The low-power engine performs speaker verification on audio input captured during the wake-up transition, so that authentication occurs simultaneously with device activation rather than as a separate subsequent step
Solution Approach 2:
Speaker verification is performed preliminarily during the wake-up transition using audio input captured while the device is transitioning from low-power to active state. This preliminary authentication ensures security is maintained while the authentication time is effectively absorbed into the wake-up time
3Reliability
If the device processes audio input for speaker verification, then user authentication is achieved, but power consumption increases
Solution Approach 1:
The low-power engine performs preliminary audio processing and speaker verification using audio input captured while the device is in or transitioning from low-power state. This preliminary action allows authentication to occur before full device activation, ensuring that power-intensive processing only occurs after necessary verification is complete
Solution Approach 2:
The system performs partial audio processing using only the low-power engine for speaker verification, rather than activating the full processing stack. The low-power engine processes audio input to extract speaker characteristics and perform verification, using minimal power compared to full device activation
Data Source
AI summary
Technologies are described herein that allow a user to wake up a computing device operating in a low-power state and for the user to be verified by speaking a single wake phrase. Wake phrase recognition is performed by a low-power engine. In some embodiments, the low-power engine may also perform speaker verification. In other embodiments, the mobile device wakes up after a wake phrase is recognized and a component other than the low-power engine performs speaker verification on a portion of the audio input comprising the wake phrase. More than one wake phrases may be associated with a particular user, and separate users may be associated with different wake phrases. Different wake phrases may cause the device transition from a low-power state to various active states.