Voice Assistant Noise Reduction via Device Coordination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In noisy environments, such as those with a TV turned on, AI speakers struggle to accurately recognize user speech due to surrounding sounds, leading to poor voice assistant performance.
Innovation Solution
An electronic device equipped with a microphone, processor, and memory that recognizes user input, converts it into a wakeup score, determines itself as a reference device based on the score, configures a noise reduction space, identifies nearby devices to perform noise reduction operations, and controls these devices to minimize noise interference.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the electronic device performs speech recognition in a noisy environment with surrounding devices operating, then the device can function in real-world scenarios, but the speech recognition accuracy deteriorates due to noise interference
Solution Approach 1:
The patent identifies noise-generating devices (TV, air conditioner, etc.) and converts their harmful noise effect into a beneficial solution by controlling these same devices to reduce or pause noise output during speech recognition operations, thereby transforming the noise source into a noise-reduction ally
Solution Approach 2:
The processor acts as an intermediary that receives speech data, identifies the user's speech intent, determines surrounding noise-generating devices, and controls these devices to reduce noise, thereby mediating between the user's speech input and the speech recognition accuracy in noisy environments
2Measurement precision
If the electronic device controls surrounding devices to reduce noise, then speech recognition accuracy improves, but the complexity of device coordination increases
Solution Approach 1:
The processor performs multiple functions: receiving speech data, recognizing user input, converting to wakeup score, determining reference device status, configuring noise reduction space, identifying noise-generating devices, and controlling noise reduction operations, thereby consolidating complex coordinated control into a single multi-functional processing unit
Solution Approach 2:
The system performs preliminary actions by configuring the noise reduction space and identifying noise-generating devices before the speech recognition process begins, ensuring that noise is reduced in advance to improve speech recognition accuracy from the outset
Data Source
AI summary
An electronic device is provided. The electronic device includes a microphone, a processor operatively connected to the microphone, and a memory operatively connected to the processor, wherein the memory, when executed, stores instructions for causing the processor to receive first speech data through the microphone, recognize a user input to call a voice assistant from the first speech data, convert the user input into a first wakeup score, determine the electronic device as a first reference device at least based on the first wakeup score that exceeds a designated threshold value, configure a first noise reduction space based on location information of the first reference device, determine at least one of one or more electronic devices, located in the first noise reduction space, as a first noise reduction device to perform a noise reduction operation, and control the noise reduction operation of the first noise reduction device.