System and/or method for semantic parsing of air traffic control audio
The method S 200 can include: at an aircraft, receiving an audio utterance from air traffic control S 210, converting the audio utterance to text, determining commands from the text using a question-and-answer model S 240, and optionally controlling the aircraft based on the commands S 250. The method functions to automatically interpret flight commands from the air traffic control (ATC) stream.
1. A system for an aircraft for semantic parsing of air traffic control (ATC) utterances, the system comprising:
a speech-to-text system configured to determine an utterance hypothesis from an ATC audio signal, wherein the utterance hypothesis comprises a spelling hypothesis associated with a waypoint entity;
a waypoint clarification system configured to:
in response to satisfaction of a waypoint clarification condition, facilitate spelling clarification via an ATC radio communication system; and
update the spelling hypothesis based on an automatic speech recognition (ASR) analysis of the spelling clarification; and
a control system configured to control the aircraft based on the aircraft commands, wherein the aircraft commands are determined based on the utterance hypothesis.
2. The system of claim 1 , wherein the speech-to-text system, the waypoint clarification system, and the control system are elements of a computing system which is located onboard the aircraft.
3. The system of claim 1 , wherein the spelling hypothesis is based on a waypoint entity lexicon.
4. The system of claim 3 , wherein the waypoint entity lexicon comprises phonetically-conflicting waypoints.
5. The system of claim 3 , wherein the spelling hypothesis is based on a subset of the waypoint entity lexicon which is associated with at least one of: the aircraft, a flight plan, or a local geographic region.
6. The system of claim 1 , wherein the waypoint clarification is based on at least one of:
a language score falling below a threshold value, wherein the language score is determined using a language model that is pretrained using waypoint pronunciations; or
a waypoint proximity relative to the aircraft which is determined using a prior map of waypoint entities.
7. The system of claim 1 , wherein the spelling hypothesis is determined with a language model, wherein the language model is updated based on the audio signal and the ASR analysis.
8. The system of claim 1 , wherein the utterance hypothesis comprises a language score at least partially associated with the waypoint entity, wherein the waypoint clarification condition comprises the language score satisfying a confidence threshold.
9. A method for semantic parsing of air traffic control (ATC) utterances, the method comprising:
determining an utterance hypothesis from an ATC audio signal, the utterance hypothesis comprising a waypoint spelling hypothesis associated with a waypoint entity;
in response to satisfaction of a waypoint clarification condition, requesting waypoint spelling clarification via an ATC radio communication system; and
updating the waypoint spelling hypothesis based on an analysis of an ATC response to the spelling clarification request; and
automatically determining an aircraft command based on the updated waypoint spelling hypothesis; and
facilitating aircraft control based on the aircraft command.
10. The method of claim 9 , further comprising: determining a language score associated with the utterance hypothesis, wherein the language score is determined using a language model that is pretrained using waypoint pronunciations, wherein the waypoint clarification condition is based on a language score falling below threshold value.
11. The method of claim 9 , wherein determining the utterance hypothesis comprises:
using automatic speech recognition, generating a plurality of linguistic hypotheses comprising a plurality of waypoint spelling hypotheses;
using a language model and contextual information, determining a language score for each the plurality of linguistic hypotheses; and
selecting an utterance hypothesis from the plurality of the linguistic hypotheses based on the corresponding language score.
12. The method of claim 9 , wherein the waypoint spelling hypothesis is determined based on a waypoint entity lexicon.
13. The method of claim 12 , wherein the waypoint entity lexicon comprises phonetically-conflicting waypoints.
14. The method of claim 9 , wherein the waypoint spelling hypothesis or the satisfaction of the waypoint clarification condition is determined based on contextual information.
15. The method of claim 14 , wherein the contextual information comprises at least one of: a location of the aircraft or an ATC tower associated with the audio signal.
16. The method of claim 9 , wherein the waypoint spelling hypothesis is determined based on a flight plan.
17. The method of claim 9 , wherein the waypoint spelling hypothesis is determined based on a local geographic region.
18. The method of claim 9 , wherein the analysis comprises and automatic speech recognition (ASR) analysis.
19. The method of claim 9 , wherein the waypoint clarification is based on a language score falling below a threshold value, wherein the language score is determined using a language model that is pretrained using waypoint pronunciations.
20. The method of claim 9 , wherein the waypoint clarification is based on a waypoint proximity relative to the aircraft which is determined using a prior map of waypoint entities.