Voice Controller Verification for Ambient Noise Rejection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice interaction devices often incorrectly recognize ambient noise or voices from other sources, leading to malfunctions and user inconvenience, as they lack effective methods to verify recognition results and account for the user's state and environment.
Innovation Solution
A controller with a microphone, sensor, and speaker that collects sound, senses the user's location, and generates audio responses to verify equipment control, inhibiting unnecessary verification statements and ensuring correct equipment operation based on user intent and environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If voice recognition is performed without verification, then user convenience is improved by prompt response, but incorrect recognition causes equipment malfunction
Solution Approach 1:
The system issues a verification utterance (e.g., 'Did you say open the window?') after initial voice recognition, requiring user confirmation before executing the command. This feedback loop allows the system to correct misrecognitions while maintaining ease of use through quick confirmation gestures or voice responses.
Solution Approach 2:
The system performs preliminary verification by detecting user presence and attention state before final command execution. By checking these conditions in advance, the system prevents incorrect operations while readying the control action, balancing speed and accuracy.
2Measurement precision
If verification utterance is always issued, then recognition accuracy is improved, but user convenience deteriorates due to repeated confirmations
Solution Approach 1:
The system dynamically adjusts verification requirements based on detected user state. When the user is detected as present and attentive, verification is performed. When the user is absent or inattentive, the system skips verification or uses alternative confirmation methods, making the interaction flow natural and convenient.
Solution Approach 2:
The system changes the verification parameter from always-required to conditionally-required based on user presence and attention detection. This parameter change allows the system to maintain high recognition accuracy when needed while improving convenience when the user state suggests confidence in the initial recognition.
3Reliability
If user presence and attention are detected, then incorrect recognition is prevented, but device complexity increases
Solution Approach 1:
The system uses a camera that serves multiple functions: capturing images for user presence detection, determining user attention state, and potentially other purposes. This multi-functionality reduces overall system complexity by consolidating detection capabilities into a single versatile component rather than requiring separate sensors for each function.
Data Source
AI summary
A method of controlling a plurality of equipment pieces by a controller including a microphone, a sensor, and a speaker includes collecting, with the microphone, sound around the controller, sensing, with the sensor, a location of a person with respect to the plurality of equipment pieces, generating sensing data based on the sensing, extracting an utterance for controlling the plurality of equipment pieces from the sound collected by the microphone, in accordance with the utterance, identifying a target equipment piece to be controlled among the plurality of equipment pieces, determining whether to control the target equipment piece based on the sensing data, when the control equipment piece is determined to be controlled, generating an audio response for verifying whether to control the target equipment piece in accordance with the utterance, and causing the speaker to output the audio response.