Voice Activation System Using Speaker as Microphone
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice activation systems in mobile audio devices face challenges in efficiently detecting speech while minimizing power consumption and reducing false positives, which can lead to increased power usage and unreliable detection.
Innovation Solution
A voice activation system that utilizes both a microphone and a speaker as dual detectors, enabling a multi-stage detection process with power modes that activate only when speech is detected, and combines signals to improve detection reliability and reduce false positives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single microphone is used for voice detection, then the device structure remains simple, but detection reliability decreases due to false positives from environmental noise
Solution Approach 1:
The patent combines the speaker and microphone into a dual-detector system where the speaker is repurposed as a second microphone. This merging approach improves detection reliability by cross-validating signals from both detectors, thereby reducing false positives from environmental noise while avoiding the need for additional dedicated microphones.
Solution Approach 2:
The speaker is given a second function by using it as a microphone for voice activity detection. This multi-functionality allows the system to achieve enhanced detection reliability without adding new hardware components, as the speaker serves both its original audio output function and the additional voice detection function.
2Reliability
If dual detectors are used to improve detection reliability, then false positives are reduced, but power consumption increases
Solution Approach 1:
The system implements periodic action by alternating between single-detector and dual-detector modes based on detection needs. The processor periodically switches between using only the microphone or both detectors, enabling the system to maintain reliability when needed while minimizing power consumption during normal operation.
Solution Approach 2:
The detection system is made dynamic by allowing the processor to adaptively switch between different operational modes (single-detector mode and dual-detector mode) based on real-time requirements. This dynamic adjustment enables the system to optimize the balance between detection reliability and power consumption flexibly.
3Speed
If continuous monitoring is performed to detect speech, then response time is reduced, but power consumption increases
Solution Approach 1:
The system uses periodic action by implementing continuous monitoring at low power through the voice activity detector, then activating full dual-detector monitoring only when speech is detected. This periodic escalation maintains fast response time while minimizing average power consumption compared to continuous high-power monitoring.
Solution Approach 2:
The voice activity detector performs preliminary action by continuously monitoring for speech at low power consumption levels. When speech is detected by this preliminary detector, it triggers the more resource-intensive dual-detector system to activate, ensuring fast response time while avoiding continuous high-power operation.
Data Source
Figure 1~2
Figure 3
Figure 4A~4B
AI summary
A voice activation system is described including a first voice activity detector for receiving a first signal from a microphone; a second voice activity detector for receiving a second signal from a speaker; a voice detector output coupled to the output of the first voice activity detector and the second voice activity detector. The first detector and the second detector are operable to generate an output signal in response to a candidate speech signal received on the respective detector inputs and the voice activation system is configured to generate a voice detector output signal when at least one of the first detector output and the second detector output indicate that speech has been detected. The voice activation system may reduce the average power consumption and increase the recognition rate of an always-on voice activation solution for headsets or other mobile audio devices.