Voice Recognition Device Non-Detecting Zone Directional Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice recognition devices often face errors due to unwanted voice recognition from unintended sources, leading to unreliable operations and inefficient resource usage.
Innovation Solution
A voice recognition device with multiple microphones that sets a non-detecting zone based on user input, skipping voice recognition for sounds originating from predetermined angles or areas, thereby reducing false triggers and conserving resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If voice recognition is performed for all received sounds, then comprehensive voice control is achieved, but false recognition from unintended sources increases and resource usage becomes inefficient
Solution Approach 1:
The patent applies local quality by creating a non-detecting zone with specific directional characteristics. The voice recognition device processes sounds differently based on their direction of origin - sounds from the non-detecting zone are skipped while sounds from other directions are processed normally. This directional differentiation improves reliability by preventing false recognition from unintended sources while maintaining efficient resource usage by not processing all sounds uniformly.
2Adaptability or versatility
If voice recognition processes all sounds equally, then no directional filtering is applied, but unwanted voice recognition from unintended sources occurs
Solution Approach 1:
The patent implements local quality by assigning different processing characteristics to sounds based on their directional origin. A non-detecting zone is established where sounds are specifically excluded from voice recognition processing, while sounds from other directions receive normal processing. This resolves the contradiction by providing adaptability through directional filtering while eliminating false recognition from unintended sources within the non-detecting zone.
3Reliability
If voice recognition is continuously performed without directional filtering, then all voice inputs are captured, but processing of unwanted sounds consumes unnecessary resources
Solution Approach 1:
The patent applies the extraction principle by removing unwanted sounds from the voice recognition processing stream. Sounds originating from the non-detecting zone are extracted and excluded from processing, while only sounds from desired directions are subjected to voice recognition. This reduces energy consumption by avoiding processing of unwanted sounds while maintaining high recognition accuracy for valid voice inputs.
4Ease of operation
If no non-detecting zone is set, then all directions are monitored for voice input, but false triggers from unintended sources increase
Solution Approach 1:
The patent resolves this contradiction by applying local quality through directional zonation. The space around the device is divided into a non-detecting zone where voice recognition is suppressed and other zones where it is active. This allows the device to maintain ease of operation by responding to voice inputs from valid directions while improving reliability by ignoring sounds from unintended sources within the non-detecting zone.
Data Source
AI summary
A voice recognition device includes a plurality of mics disposed toward different directions and a processor connected with the plurality of mics, wherein the processor is configured to determine, in a setup mode, a direction of a first sound received through the plurality of mics; set a non-detecting zone, which includes the direction of the first sound; determine, in a normal mode, a direction of a second sound received through the plurality of mics; and skip voice recognition for the second sound or an operation based on the voice recognition depending on whether the direction of the second sound belongs to the non-detecting zone.