Emerging
Jun 18, 20261
66%
ASTRA: AI-Powered Air Traffic Control Training Simulator Reduces Speech Recognition Errors in Singapore

ASTRA is a new AI-powered training simulator that automates the role of simpilots in air traffic control operator training. The system uses locally adapted speech recognition that reduces word error rates from 107.80% to 23.45% for Singaporean-accented aviation speech, and includes an AI performance evaluator that assesses trainee communications with 86–92% accuracy.

Quick Facts
Who
Air Traffic Control Operators (ATCOs)
What
Development of an end-to-end ATCO training simulator
When
Submitted 16 June 2026
Where
Singapore (operational context)
- Development of an end-to-end ATCO training simulator
- Automation of simpilot roles through AI pipeline
- Fine-tuned Automatic Speech Recognition for aviation speech
- AI-assisted performance evaluation framework for trainee communications
- Adaptation of speech models to regional (Singaporean) contexts
Researchers have introduced ASTRA, a next-generation training simulator designed to automate the role of simpilots—specialized human trainers who role-play as both pilots and air traffic control operators during training exercises. The system addresses a critical bottleneck in Air Traffic Control Operator (ATCO) training capacity by leveraging artificial intelligence to replace manual instruction roles while maintaining high-quality performance evaluation.
A key innovation of ASTRA is its adaptation to regional speech patterns. Existing automated training solutions rely on Western-centric speech recognition models that perform poorly in non-Western operational contexts. Off-the-shelf systems exhibited Word Error Rates (WER) of up to 107.80% when processing Singaporean-accented aviation speech—rendering them effectively unusable in that setting. ASTRA's fine-tuned Automatic Speech Recognition (ASR) pipeline dramatically reduces this error rate to 23.45%, making it substantially more effective for regional deployment.
Beyond speech recognition, ASTRA incorporates an AI-assisted performance evaluation framework that assesses trainee radiotelephony communications across three critical dimensions. The system evaluates accuracy, brevity, and completeness of communications, achieving post-optimization assessment scores of 91.7%, 88.2%, and 86.9% respectively. This automated evaluation standardizes training assessment while reducing the workload on human instructors.
The system is built on open-source foundations including DSPy and Unsloth, enabling scalability and accessibility. By automating simpilot roles, ASTRA addresses training capacity constraints while maintaining training quality through rigorous AI-powered assessment. The approach represents a shift toward standardized, technology-enabled ATCO training that can be adapted to regional speech and operational contexts.
Why This Matters
ASTRA addresses a critical capacity bottleneck in aviation training by automating expensive human instruction roles while maintaining training quality. For Singapore and other non-Western aviation hubs, the system's regional speech adaptation is transformative—existing Western-centric tools were essentially unusable (107.80% error rate). This enables scalable, standardized ATCO training that can be rapidly deployed across regional aviation systems, improving operational readiness while reducing instructor workload and training costs.
Timeline & Sources
Jun 16, 2026
WireASTRA paper submitted to arXiv
Jun 18, 2026
WireASTRA paper published on arXiv (cs.LG category)