Hearable Voice Detection via Dual Microphone Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice-enabled battery-powered devices, such as hearable devices, face reduced battery life due to power-intensive voice-processing techniques, making it impractical to enable voice control in devices with small batteries.
Innovation Solution
Implementing a method using dual microphones, an in-ear microphone and an exterior microphone, to differentiate user voice commands from background noise by analyzing correlations between the two audio signals, thereby reducing unnecessary power consumption by only performing voice-processing techniques when a valid voice command is detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If voice-processing techniques are continuously performed to enable voice control, then voice command detection capability is improved, but battery life is reduced due to increased power consumption
Solution Approach 1:
The patent performs preliminary voice command detection by analyzing audio signals before initiating full voice-processing techniques. The hearable device continuously monitors audio input using low-power preprocessing to identify potential voice commands, then activates more power-intensive processing only when a voice command is detected. This preliminary action approach allows the device to maintain voice control capability while significantly reducing overall power consumption and extending battery life.
2Use of energy by moving object
If voice-processing techniques are performed only when needed, then power consumption is reduced, but voice command detection accuracy may be compromised
Solution Approach 1:
The patent segments the voice detection process into multiple stages: a low-power preliminary detection stage that continuously monitors audio input, and a high-accuracy processing stage that activates only when a voice command is detected. The preliminary stage uses simplified algorithms to identify potential voice commands, while the second stage employs more sophisticated processing to confirm the detection with high accuracy. This segmentation ensures both power efficiency and detection accuracy.
Solution Approach 2:
The patent introduces an intermediary preliminary detection mechanism that acts as a gateway between continuous audio monitoring and full voice processing. This intermediary layer filters out non-voice sounds and preliminary analyzes audio patterns to determine whether full processing is warranted. By using this intermediary, the system maintains high detection accuracy while avoiding unnecessary power consumption from continuous full-scale processing.
3Measurement precision
If dual microphones are used to differentiate voice commands from background noise, then detection accuracy is improved, but device complexity increases
Solution Approach 1:
The patent combines signals from multiple microphones into a unified audio processing pipeline. By merging the audio inputs from different microphone elements and applying correlated processing techniques, the system achieves improved voice command differentiation without requiring separate complex processing paths for each microphone. This merging approach maintains high detection accuracy while reducing overall system complexity compared to independent processing of each microphone channel.
Data Source
AI summary
Techniques for detecting a voice command from a user of a hearable device. The hearable device may include an in-ear facing microphone to capture sound emitted from an ear of the user, and an exterior facing microphone to capture sound emitted from an exterior environment of the user. The in-ear microphone may generate an in-ear audio signal representing the sound emitted from the ear, and the exterior microphone may generate an exterior audio signal representing sound from the exterior environment. The hearable device may include components to determine correlations or similarities between the in-ear audio signal and exterior audio signal, which indicate that the audio signals represent sound emitted from the user. Further, the components may perform voice activity detection to determine that the sound emitted from the user is a voice command, and proceed to perform further voice-processing techniques.