Voice Recognition Buffering for Standby Power Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Image display devices with remote voice recognition functions face challenges in satisfying standby power regulations due to the need to maintain power for voice recognition modules even in a power-off state, leading to difficulties in minimizing power consumption.
Innovation Solution
The implementation of an image display device and voice recognition method that stores received utterance data in multiple buffers, allowing for consecutive command recognition after a wake-up word is detected, while minimizing power usage by resetting the digital signal processing unit and utilizing the microcontroller for data storage during system booting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If power is supplied to the voice recognition module in a power-off state to enable wake up word detection, then the wake up word recognition function is improved, but the standby power consumption increases
Solution Approach 1:
The voice recognition module is divided into two independent parts: a digital signal processing unit that remains active in power-off state for wake up word detection, and a microcontroller that is reset after wake up word recognition. This segmentation allows the system to maintain minimal power consumption while preserving the wake up word recognition function.
Solution Approach 2:
The digital signal processing unit performs preliminary wake up word detection before the microcontroller is activated. By completing the wake up word recognition in advance during the power-off state, the system can then reset the digital signal processing unit and activate the microcontroller only when needed, reducing overall power consumption.
2Ease of operation
If the digital signal processing unit is reset after wake up word recognition, then the system is prepared for normal operation, but utterance data may be lost during the reset and booting process
Solution Approach 1:
A buffer is introduced as an intermediary storage device between the digital signal processing unit and the microcontroller. The buffer stores utterance data received during the power-off state, ensuring that data is preserved even when the digital signal processing unit is reset and the microcontroller is activated during booting.
Solution Approach 2:
The buffer stores utterance data in advance before the digital signal processing unit is reset. By performing the data storage action beforehand, the system ensures that no utterance data is lost during the subsequent reset and booting process, while still preparing the system for normal operation.
3Reliability
If multiple buffers are used to store utterance data from different sources, then data security and continuity are improved, but the device complexity increases
Solution Approach 1:
The buffer memory is divided into multiple segments: a first buffer for storing utterance data from the power-off state, a second buffer for storing utterance data from the power-on state, and a third buffer for storing wake up word data. This segmentation allows each buffer to have a specific function, improving data security and continuity while keeping the management structure organized and manageable.
Solution Approach 2:
Each buffer is assigned a specific local function with distinct characteristics: the first buffer handles pre-power-off data, the second buffer handles post-power-on data, and the third buffer handles wake up word verification. This local quality assignment allows each buffer to be optimized for its specific purpose, improving overall system reliability without requiring complex unified management.
Data Source
AI summary
An image display device and a voice recognition method thereof are proposed. The image display device and voice recognition method thereof stores received first utterance data in a first buffer when a wake up word is recognized from utterance data, stores second utterance data consecutively uttered from a user in a second buffer, stores third utterance data consecutively uttered from the user in a third buffer when verification of the wake up word is successful on the basis of the first utterance data after booting of an operating system is completed, and joins the second uttered data and the third uttered data respectively stored in the second buffer and the third buffer, so as to perform voice recognition for the utterance data consecutively uttered by the user. Accordingly, including the commands uttered at intervals after the wake up word, user's commands that are consecutively uttered may be recognized.