Voice Wakeup Normalization for Multi-Device Ambience
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multi-device scenarios, such as smart homes, the same voice wakeup keyword is often set across multiple electronic devices, leading to confusion when activated, affecting user experience as multiple devices wake up simultaneously.
Innovation Solution
A third-party device normalizes the energy values of voice wakeup keywords from multiple electronic devices based on ambient sound energy and sound collection capabilities to determine which device to wake up, reducing the impact of ambient noise and hardware capabilities on accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the same wakeup keyword is set in multiple electronic devices, then the user can wake up any device in the multi-device scenario, but multiple devices will be woken up simultaneously causing confusion and affecting user experience
Solution Approach 1:
The patent applies local quality by making each electronic device have different wakeup keyword energy thresholds based on their individual sound collection capabilities. Devices with better microphones can detect lower energy keywords, while devices with poorer microphones require higher energy keywords. This differentiated approach ensures that only the intended device wakes up, eliminating the confusion caused by multiple devices responding to the same keyword.
2Device complexity
If electronic devices with different sound collection capabilities use the same wakeup keyword energy threshold, then the system is simple to implement, but devices with better sound collection capabilities will incorrectly wake up due to higher received energy
Solution Approach 1:
The patent changes the energy threshold parameter dynamically based on each device's sound collection capability. Devices report their microphone quality to the server, which then assigns appropriate energy thresholds. High-quality microphones receive lower thresholds, while low-quality microphones receive higher thresholds. This parameter adjustment resolves the contradiction by maintaining simple implementation while achieving accurate wakeup differentiation.
3Device complexity
If the system does not normalize wakeup keyword energy values, then the processing is simpler, but ambient sound and device capabilities significantly impact wakeup accuracy
Solution Approach 1:
The patent introduces a server as an intermediary that normalizes wakeup keyword energy values from multiple devices. The server receives raw energy values, adjusts them based on each device's sound collection capability and ambient noise conditions, and determines which device should wake up. This intermediary approach maintains reasonable processing complexity while significantly improving wakeup reliability through centralized normalization.
Data Source
AI summary
A voice wakeup method and a device are provided. The method includes: receiving, by a third-party device, wakeup messages sent by at least two electronic devices, where the wakeup message includes wakeup keyword energy information used to indicate a wakeup keyword energy value, and the wakeup keyword energy value; normalizing wakeup keyword energy values based on ambient sound energy and/or sound collection capabilities of devices, to obtain at least two normalized wakeup keyword energy values; and based on the at least two normalized wakeup keyword energy values, sending a wakeup permission instruction to a first electronic device in the at least two electronic devices, and sending a wakeup prohibition instruction to another electronic device other than the first electronic device, where a normalized wakeup keyword energy value of the first electronic device is a maximum value. This helps improve accuracy of waking up a device nearby in a multi-device scenario.