In-Vehicle Voice Detector Bypass for Faster Assistant Activation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing in-vehicle voice assistant systems experience delays in activating the voice assistant function when a wake-up word is detected, which can be inconvenient for users while driving.
Innovation Solution
An in-vehicle apparatus equipped with a voice detector and interface that performs voice recognition and communicates directly with a connected mobile device to quickly activate the voice assistant function by sending the detected wake-up word, bypassing the need for the voice detector to send the audio signal.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If the audio signal is sent through the voice detector for voice recognition processing, then the voice recognition function can be performed, but the activation time of the voice assistant function increases
Solution Approach 1:
The patent segments the signal processing path into two separate paths: one path through the voice detector for comprehensive voice recognition, and another direct path from the microphone to the interface for rapid wake-up word detection. This segmentation allows the system to handle different types of voice inputs through different paths, achieving both speed and accuracy.
Solution Approach 2:
The patent implements preliminary action by having the interface directly receive and process audio signals from the microphone without waiting for the voice detector's processing. The interface can independently detect wake-up words and activate the voice assistant function before the voice detector completes its full voice recognition process, thereby reducing activation time.
2Ease of operation
If the voice assistant function is activated by wake-up word detection, then the user can conveniently initiate commands, but the activation process takes more time than necessary
Solution Approach 1:
The patent introduces the interface as an intermediary component that directly connects the microphone to the voice assistant function activation process. This intermediary bypasses the voice detector for wake-up word detection, creating a dedicated fast path that maintains ease of operation while significantly improving activation speed.
Solution Approach 2:
The system dynamically selects different processing paths based on the type of voice input. For wake-up word detection, it uses the direct fast path through the interface. For other voice recognition tasks, it uses the comprehensive processing path through the voice detector. This dynamic path selection optimizes both user convenience and activation speed.
Data Source
AI summary
An in-vehicle apparatus is connectable to a device that includes a voice assistant function. The in-vehicle apparatus includes: a voice detector that performs voice recognition of an audio signal input from a microphone and that controls functions of the in-vehicle apparatus based on a result of the voice recognition; and an interface that communicates with the device. When being informed of a detection of a predetermined word in the audio signal as the result of the voice recognition of the audio signal performed by the voice detector, the interface sends to the device, not via the voice detector, the audio signal input from the microphone. The predetermined word is for activating the voice assistant function of the device.