Automatic Processing Pipeline for Collecting and Annotating Air-Traffic Voice Communication Data

This document describes our pipeline for automatic processing of ATCO pilot audio
communication we developed as part of the ATCO2 project. So far, we collected two thousand hours
of audio recordings that we either preprocessed for the transcribers or used for semi-supervised
training. Both methods of using the collected data can further improve our pipeline by retraining our
models. The proposed automatic processing pipeline is a cascade of many standalone components:
(a) segmentation, (b) volume control, (c) signal-to-noise ratio filtering, (d) diarization, (e) speech-totext
(ASR) module, (f) English language detection, (g) call-sign code recognition, (h) ATCOpilot
classification and (i) highlighting commands and values. The key component of the pipeline is a
speech-to-text transcription system that has to be trained with real-world ATC data; otherwise, the
performance is poor. In order to further improve speech-to-text performance, we apply both semisupervised
training with our recordings and the contextual adaptation that uses a list of plausible
callsigns from surveillance data as auxiliary information. Downstream NLP/NLU tasks are important
from an application point of view. These application tasks need accurate models operating on top of
the real speech-to-text output; thus, there is a need for more data too. Creating ATC data is the main
aspiration of the ATCO2 project. At the end of the project, the data will be packaged and distributed
by ELDA.