Voice Recognition Activation via Door Sensor Dynamics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice recognition devices require a wake-up word to activate the voice recognition function, limiting natural user interaction and leading to excessive power and processing resource consumption when the function is activated continuously, even if not intended for use.
Innovation Solution
An apparatus with a voice recognition capability that uses sensors to detect user actions such as opening or closing a door, or rearranging objects, to determine when a voice command is intended, thereby activating the voice recognition function without a wake-up word, and includes a controller to manage the voice recognizer's active and inactive states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the voice recognition function is activated continuously to enable natural voice interaction without wake-up word, then the ease of operation is improved, but the power consumption and processing resource consumption increase excessively
Solution Approach 1:
The voice recognition function dynamically transitions between inactive and active states based on detected user actions. The system activates the voice recognition function only when specific actions are detected (door open/close, object addition/removal, object rearrangement), rather than maintaining continuous activation. This dynamic state change resolves the contradiction by enabling natural voice interaction when needed while conserving power during normal operation.
Solution Approach 2:
The system performs preliminary detection of user actions (door operations, object changes) before activating the voice recognition function. By detecting these triggering actions in advance, the system prepares to activate voice recognition only when necessary, avoiding continuous power consumption while ensuring readiness for natural voice interaction when the user intends to communicate.
2Ease of operation
If the voice recognition function is activated continuously to recognize voice commands without wake-up word, then the ease of operation is improved, but erroneous operations occur when the user does not intend voice interaction
Solution Approach 1:
The voice recognition function dynamically transitions between inactive and active states based on detected user actions. The system activates the voice recognition function only when specific actions are detected (door open/close, object addition/removal, object rearrangement), rather than maintaining continuous activation. This dynamic state change resolves the contradiction by enabling natural voice interaction when needed while conserving power during normal operation.
Solution Approach 2:
The system uses feedback from action detectors (door sensors, object detection mechanisms) to determine when to activate the voice recognition function. By monitoring user actions and providing feedback signals to control activation, the system ensures voice recognition is enabled only when the user intends to interact, preventing erroneous operations while maintaining ease of natural voice interaction.
3Use of energy by moving object
If a wake-up word is required to activate voice recognition, then the power consumption is reduced, but the ease of operation deteriorates as natural conversation cannot be performed
Solution Approach 1:
The invention extracts and removes the wake-up word requirement from the voice interaction process. Instead of requiring users to speak a specific wake-up word, the system detects user actions (door operations, object changes) as implicit triggers for voice recognition activation. This extraction of the wake-up word mechanism while maintaining action-based activation resolves the contradiction by enabling natural conversation without the energy overhead of continuous voice recognition.
Solution Approach 2:
The system introduces user actions (door open/close, object addition/removal, object rearrangement) as intermediary triggers between the user's intent to interact and the voice recognition activation. These actions serve as mediators that signal when voice recognition should be activated, replacing the wake-up word mechanism while maintaining power efficiency and enabling natural interaction.
Data Source
AI summary
The present disclosure relates to an apparatus which communicates with a voice recognition device, and a method for controlling an apparatus with a voice recognition capability which operates in the Internet of Things environment configured by a 5G communication network. According to an exemplary embodiment of the present disclosure, an apparatus with a voice recognition capability includes a container which has one open surface and accommodates objects therein, a door which opens/closes the container, a sensor which senses an open/closed state of the door, a microphone which receives an external voice, a voice recognizer which recognizes a voice command received from the microphone, and a controller which controls an active state and an inactive state of the voice recognizer, in which the controller may predict whether the voice recognizer needs to be activated using a deep neural network model learned through the machine learning.