Year: 2026
Type: article
Abstract: Transcription of aviation communications has several applications, from assisting air traffic controllers in identifying the accuracy of read-back errors to search and rescue operations. Recent advances in artificial intelligence have provided unprecedented opportunities for improving aviation communication transcription tasks. OpenAI’s Whisper is one of the leading automatic speech recognition models. However, fine-tuning Whisper for aviation communication transcription is not computationally efficient. Thus, this paper aims to use a parameter-efficient fine-tuning method called low-rank adaptation to fine-tune a more computationally efficient version of Whisper, Distil-Whisper. To perform the fine-tuning, we used the Air Traffic Control Corpus dataset from the Linguistic Data Consortium, which contains approximately 70 h of controller and pilot transmissions near three major airports in the United States. The objective was to reduce the word error rate to enhance accuracy in the transcription of aviation communication. First, starting with an initial set of hyperparameters for Low-Rank Adaptation (LoRA) ([Formula: see text]), we performed a grid search. We applied a fivefold cross-validation to find the best combination of Distil-Whisper hyperparameters. Then, we fine-tuned the model for LoRA hyperparameters, achieving an impressive average word error rate of 3.86% across five folds. This result highlights the model’s potential for use in the cockpit.
DOI: 10.2514/1.i011656
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Air Force Research Laboratory
Award: G5871797506
OpenAlex ID: W4417066003
FWCI:
Cites:
Cited by:
Related to: