Vehicle Voice Wake-Up Zone Selection via Amplitude Analysis
Solution Overview
Problem
Vehicle-mounted terminals experience low voice wake-up accuracy due to insufficient sound isolation between audio zones, leading to misidentification of the source of voice signals and simultaneous activation of multiple zones.
Innovation Solution
A voice wake-up processing method that acquires voice wake-up signals from multiple audio zones, determines the amplitude of these signals, and uses a voice engine to identify the correct zone by comparing amplitudes and sound isolation levels, ensuring only the intended zone is activated.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a microphone array is provided in each audio zone to enable voice interaction for all vehicle members, then the service coverage is improved, but the voice wake-up accuracy deteriorates due to insufficient sound isolation between zones
Solution Approach 1:
The vehicle interior is divided into four independent audio zones (front, rear, left, right) with separate microphone arrays for each zone. This segmentation allows the system to provide services to all vehicle members while enabling independent voice wake-up processing for each zone, resolving the contradiction between service coverage and wake-up accuracy.
Solution Approach 2:
Each audio zone is equipped with its own microphone array with optimized directional characteristics tailored to that specific zone. The front zone microphone array faces forward, the rear zone array faces backward, and side zone arrays face laterally. This local optimization ensures each array primarily captures voices from its designated zone while reducing cross-zone interference.
2Object-affected harmful factors
If microphone array algorithms are used to create audio isolation between zones, then sound separation is improved, but voice wake-up accuracy still deteriorates due to residual cross-zone signal collection
Solution Approach 1:
The system changes the parameter of amplitude threshold for wake-up signal detection. By setting a predetermined amplitude threshold and only activating zones where the wake-up signal exceeds this threshold, the system effectively filters out cross-zone signals that have attenuated during transmission, thereby improving wake-up accuracy while maintaining sound separation capabilities.
Solution Approach 2:
The voice engine analyzes the wake-up signal characteristics from each zone's microphone array and provides feedback to determine which zone should be activated. This feedback mechanism allows the system to distinguish between genuine wake-up commands from a specific zone and cross-zone signals, resolving the accuracy issue despite residual signal collection.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Improves the accuracy of voice wake-up results by correctly identifying the zone where the user is located, preventing simultaneous activation and enhancing user experience.
Implementation Method 1
acquiring voice wake-up signals collected by audio input devices in at least two audio zones; determining, according to amplitudes of the voice wake-up signals
Data Source
AI summary
The present disclosure provides a voice wake-up processing method, an apparatus and a storage medium. After acquiring voice wake-up signals collected by audio input devices in at least two audio zones, an electronic device may correct, based on to-be-woken-up audio zones obtained from amplitudes of the voice wake-up signals collected by the audio input devices in the at least two audio zones, a to-be-woken-up audio zone identified using a voice engine, avoiding that audio zones in which a plurality of audio input devices collecting voice wake-up signals produced from a same user are located are all woken up, therefore, it is possible to improve accuracy of a voice wake-up result obtained by the electronic device. Therefore, the present disclosure can solve the technical problem that a vehicle-mounted terminal has low voice wake-up accuracy due to an insufficient degree of sound isolation between audio zones of the vehicle-mounted terminal.