Voice Assistant Wake-Up Using Wrist Motion and Approaching Speech
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current voice assistant interaction methods face issues such as privacy concerns in public places, lengthy interactions, and cumbersome button operations, leading to inefficiencies and potential accidental screen activation.
Innovation Solution
A method utilizing inertial measurement unit (IMU) data and illuminance data to detect wrist or hand raising actions, followed by microphone activation and voice assistant initiation upon detecting approaching human voice, with additional checks for maintaining the action, reducing false wake-ups and power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If wake-up word recognition is used, then voice assistant can be activated, but privacy issues arise in public places and interaction becomes lengthy
Solution Approach 1:
The system performs preliminary actions by detecting wrist raising motion and approaching human voice before full voice assistant activation. The motion sensor detects wrist raising, then the microphone captures approaching human voice, enabling faster activation than traditional wake-up word methods.
2Reliability
If physical button operation is used, then device can be activated, but large force and delay are required, and accidental screen activation may occur
Solution Approach 1:
The patent replaces mechanical button pressing with motion sensing technology. The motion sensor detects wrist raising action, substituting the mechanical button system with an optical/electromagnetic sensing system that requires no physical contact, eliminating accidental activations and reducing operational complexity.
3Measurement precision
If only acceleration data is used for event detection, then device complexity is reduced, but detection sensitivity is insufficient for natural wrist raising
Solution Approach 1:
The system merges multiple data sources including acceleration data from motion sensors, illuminance data from light sensors, and audio data from microphones. This combination provides comprehensive detection of natural wrist raising actions, with each sensor type contributing complementary information to achieve high detection accuracy.
Data Source
AI summary
A speech interaction method and a related device are provided, and relate to the artificial intelligence field. A first device obtains IMU data and illuminance data of the first device when detecting a first event (S201); determines, based on the IMU data and the illuminance data of the first device, whether a user performs a first preset action (S202); if the first device determines that the user performs the first preset action, starts a microphone of the first device, and obtains a first audio signal collected by the microphone (S203); determines, based on the first audio signal, whether a type of the first audio signal is an approaching human voice (S204); and starts a voice assistant of the first device if the first device determines that the type of the first audio signal is the approaching human voice (S205).