Avionics Voice Recognition Using Keyword Frequency Encoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice recognition systems in avionics environments face challenges due to unique grammar rules and extensive character collections, limiting their applicability and requiring complex grammar sets, which existing technologies have not adequately addressed.
Innovation Solution
An avionics system that automatically tunes communication radio frequencies using voice recognition by equating specific keywords to radio frequencies, employing a Push-To-Recognize switch, Adaptive Flight Display, voice recognition subsystem, ARINC Graphics Server, and Radio Tuning System Application to process voice commands and display results, allowing pilots to tune radios by speaking keywords like 'EMERGENCY' for 121.5 MHz.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional voice recognition systems use comprehensive grammar sets to recognize aviation terms and frequencies, then recognition accuracy improves, but system complexity and difficulty of implementation increase significantly
Solution Approach 1:
The patent segments the voice recognition task into two distinct phases: frequency identification (using simple keyword matching for frequencies like 121.5, 118.5) and location identification (using dynamic grammar for place names). This segmentation allows each phase to use the most appropriate recognition method, reducing overall system complexity while maintaining accuracy.
Solution Approach 2:
The patent implements dynamic grammar that adapts based on the current operational context. The system dynamically adjusts which grammar rules are active depending on whether the pilot is specifying a frequency, a location, or performing another function. This dynamic approach reduces the complexity of the grammar set needed at any given moment while maintaining comprehensive recognition capability.
2Measurement precision
If voice recognition systems require pilots to speak complete frequency numbers (e.g., 1 2 1 5 for 121.5 MHz), then frequency tuning precision is maintained, but ease of operation decreases
Solution Approach 1:
The patent creates a simplified verbal representation (copy) of the frequency that pilots need to speak. Instead of requiring pronunciation of individual digits, the system accepts natural speech patterns and maps them to frequency values. The voice recognition system copies the intent from natural speech and translates it into the precise frequency control signal, maintaining precision while improving ease of operation.
3Adaptability or versatility
If voice recognition systems use dynamic grammar based on previous commands, then adaptability improves, but reliability decreases in aviation environments where grammar must be detached and fragmented
Solution Approach 1:
The patent applies different grammar characteristics to different functional areas. Frequency-related commands use simple, rigid keyword matching for maximum reliability, while location-related commands use dynamic grammar for adaptability. This local differentiation allows each subsystem to have the grammar characteristics best suited to its specific requirements, maintaining overall system reliability while providing necessary adaptability.
Data Source
AI summary
An avionics system, including a means to tune communication radio frequencies utilizing a voice recognition system. A specific feature of this mode of initiation is the automatic radio tuning of communication VHF radios by the utterance of specific key words resulting in the automatic transference of letters to numbers.