Contextual Speech Recognition Graph for Aircraft Clearances
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current aircraft systems face challenges in accurately inputting air traffic control clearances due to the risk of incomplete or incorrect entries, which can compromise aircraft control, highlighting the need for improved methods to facilitate accurate and efficient communication and data entry in cockpit displays.
Innovation Solution
The implementation of a contextual speech recognition system that predicts potential input elements based on air traffic control communications, constructs a limited command vocabulary, and uses a contextual speech recognition graph to quickly and accurately recognize audio inputs, thereby reducing errors and improving response time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a full command vocabulary is used for speech recognition, then the system can handle diverse inputs, but recognition accuracy decreases due to ambiguity and incorrect interpretations
Solution Approach 1:
The patent applies local quality by dynamically adapting the command vocabulary size and scope based on the specific input element being accessed. When a pilot selects an input element, the system constructs a speech recognition graph with a command vocabulary tailored to that specific element's context, using only the relevant subset of commands rather than the full vocabulary. This localized approach improves recognition accuracy for each specific input element while maintaining overall system versatility.
Solution Approach 2:
The system dynamically adjusts the command vocabulary based on runtime conditions. The speech recognition graph is constructed on-demand when an input element is selected, rather than using a static full vocabulary. This dynamic adaptation allows the system to optimize the command set for each specific context, improving recognition accuracy while maintaining the ability to handle diverse inputs across different elements.
2Measurement precision
If speech recognition processing is performed in real-time without pre-construction, then the system responds quickly to user input, but recognition accuracy decreases due to lack of contextual preparation
Solution Approach 1:
The system performs preliminary action by pre-constructing the speech recognition graph and command vocabulary subset before the pilot actually provides speech input. When an input element is selected on the display, the system proactively builds the contextual speech recognition graph with the appropriate command vocabulary for that element. This preparation happens before the speech recognition task, ensuring both high accuracy and quick response time when the pilot speaks.
Data Source
AI summary
Methods and systems are provided for assisting operation of a vehicle using speech recognition. One method involves automatically identifying an input element based at least in part on an audio communication with respect to the vehicle, identifying one or more constraints associated with the input element, obtaining a limited command vocabulary for the input element using the one or more constraints, and automatically constructing a contextual speech recognition graph for the input element prior to user selection of the input element using the limited command vocabulary. Thereafter, subsequently received audio input is recognized using the contextual speech recognition graph that was automatically and prospectively generated.