Hand-Sensing Input Device for Complete Speech Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing input devices face issues with speech recognition errors due to incomplete utterances and the need for precise pointing, especially when using remote controllers.
Innovation Solution
An input device with a sensor, microphone, and processor that initiates speech recognition through user operations like hovering, swiping, or touching, providing feedback and transmitting voice signals to an electronic device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the speech recognition button is pressed at the same time as the utterance is started, then the speech recognition can be initiated, but the initial sound is not input
Solution Approach 1:
The system performs preliminary action by detecting the user's hand approach before the button is pressed. When the hand approaches the button within a predetermined time period before pressing, the system captures and stores the initial sound separately, then combines it with the subsequent speech recognition input. This ensures the initial sound is not lost even though the button was pressed at the same time as the utterance started.
2Ease of operation
If the hand is removed from the speech recognition button before the utterance ends, then the button operation is completed, but the input device cannot recognize a complete sentence
Solution Approach 1:
The system implements feedback by continuously monitoring whether the hand is present on the button during the utterance. If the hand is removed before the utterance ends, the system detects this through the sensor signal changes and provides feedback to the user (e.g., through visual or haptic indicators) to inform them that the speech recognition is incomplete. This allows the user to understand the current state without requiring continuous physical contact.
3Ease of operation
If a remote controller is designed in a stick form, then it can be controlled, but the user has to point the remote controller toward the direction of the electronic device
Solution Approach 1:
The system replaces the mechanical pointing requirement with an optical sensing mechanism. Instead of requiring the user to physically point the remote controller at the electronic device, the system uses a sensor (such as an optical sensor or camera) to detect the user's hand approach and position. This substitution eliminates the need for precise pointing while maintaining control functionality, as the sensor can detect the user's presence and intent without requiring direct line-of-sight alignment.
4Reliability
If the microphone is activated continuously for speech recognition, then complete sentences can be captured, but energy consumption increases
Solution Approach 1:
The system implements periodic action by activating the microphone in intervals rather than continuously. The microphone is activated when the sensor detects a hand approach to the button, and it remains active only during the speech recognition period. After capturing the necessary speech input, the microphone is deactivated. This periodic activation pattern ensures complete sentences are captured when needed while significantly reducing energy consumption compared to continuous operation.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances user convenience by allowing simple and accurate speech recognition control of electronic devices with real-time feedback on recognition status.
Implementation Method 1
The sensor may include at least one light output member and a light intensity measuring member. The processor may control the at least one light output member to output light and identify the operation based on a reflected amount of the output light measured via the light intensity measuring member.
Data Source
Figure 1~2
Figure 3a~3c
Figure 4
AI summary
An input device which includes a sensor, a microphone, a communicator, and a processor configured to, based on an operation of a user being identified based on a value sensed through the sensor, transmit utterance intention sensing information to an electronic device, based on a command to initiate a speech recognition and feedback information being received from the electronic device according to the utterance intention sensing information transmitted to the electronic device, activate the microphone and provide a feedback according to the feedback information, and transmit a voice signal received via the microphone to the electronic device.