Display Voice Recognition Using External Command Word Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice recognition systems in electronic devices have limitations such as fixed input means, slow processing speed due to large numbers of candidate instruction words, and limited storage capacity, making them inefficient for various input methods and recognition rates.
Innovation Solution
A display apparatus with multiple voice acquiring units, including built-in and external microphones, communicates with external devices to receive candidate instruction words, enabling voice recognition through a controller that manages and processes voice signals using a voice recognition engine.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple voice acquiring units are used to enable various input means, then adaptability is improved, but device complexity increases
Solution Approach 1:
The display apparatus is designed to perform multiple functions by integrating both image display and voice recognition capabilities. The system can receive inputs from multiple voice acquiring units (built-in microphone and external microphones) and process both visual and audio information, making it a universal device that adapts to various input methods without requiring separate dedicated devices.
Solution Approach 2:
The controller acts as an intermediary that manages communication between multiple voice acquiring units, external devices, and the voice recognition engine. It coordinates the selection of active voice acquiring units based on detection results and manages the transmission of voice signals and candidate instruction words, thereby handling the complexity of multiple input sources through a centralized control mechanism.
2Measurement precision
If many candidate instruction words are provided to increase recognition rate, then measurement precision is improved, but productivity deteriorates due to slower processing speed
Solution Approach 1:
Candidate instruction words are pre-stored in external devices before the voice recognition process begins. When voice input is detected, the system retrieves these pre-prepared candidate words from external devices rather than generating or searching for them in real-time, significantly reducing processing time while maintaining a large number of recognition options.
Solution Approach 2:
The voice recognition system extracts and utilizes candidate instruction words from external devices (such as mobile phones or remote controllers) rather than storing all possible candidate words within the display apparatus itself. This extraction approach allows the system to access a large vocabulary for accurate recognition while keeping the main device's storage and processing requirements manageable.
3Measurement precision
If candidate instruction words are stored in the main apparatus to enable recognition, then measurement precision is improved, but storage capacity is exceeded
Solution Approach 1:
The system segments the storage function by dividing candidate instruction words between the display apparatus and external devices. The display apparatus stores only essential data structures and recently used candidates, while external devices store the comprehensive vocabulary database. This segmentation allows accurate recognition without overwhelming the main apparatus's storage capacity.
Solution Approach 2:
External devices serve as intermediaries that provide candidate instruction words to the display apparatus. Rather than the display apparatus directly storing all candidate words, the external devices act as intermediate storage repositories, transmitting candidate words to the display apparatus only when needed for recognition, thereby reducing the storage burden on the main device.
Data Source
AI summary
Disclosed are a display apparatus, a voice acquiring apparatus and a voice recognition method thereof, the display apparatus including: a display unit which displays an image; a communication unit which communicates with a plurality of external apparatuses; and a controller which includes a voice recognition engine to recognize a user's voice, receives a voice signal from a voice acquiring unit, and controls the communication unit to receive candidate instruction words from at least one of the plurality of external apparatuses to recognize the received voice signal.