Air Traffic Control Communications Research Articles

Assessment and analysis of accents in air traffic control speech: a fusion of deep learning and information theory.

Enhancing the generalization and reliability of speech recognition models in the field of air traffic control (ATC) is a challenging task. This is due to the limited storage, difficulty in acquisition, and high labeling costs of ATC speech data, which may result in data sample bias and class imbalance, leading to uncertainty and inaccuracy in speech recognition results. This study investigates a method for assessing the quality of ATC speech based on accents. Different combinations of data quality categories are selected according to the requirements of different model application scenarios to address the aforementioned issues effectively. The impact of accents on the performance of speech recognition models is analyzed, and a fusion feature phoneme recognition model based on prior text information is constructed to identify phonemes of speech uttered by speakers. This model includes an audio encoding module, a prior text encoding module, a feature fusion module, and fully connected layers. The model takes speech and its corresponding prior text as input and outputs a predicted phoneme sequence of the speech. The model recognizes accented speech as phonemes that do not match the transcribed phoneme sequence of the actual speech text and quantitatively evaluates the accents in ATC communication by calculating the differences between the recognized phoneme sequence and the transcribed phoneme sequence of the actual speech text. Additionally, different levels of accents are input into different types of speech recognition models to analyze and compare the recognition accuracy of the models. Experimental results show that, under the same experimental conditions, the highest impact of different levels of accents on speech recognition accuracy in ATC communication is 26.37%. This further demonstrates that accents affect the accuracy of speech recognition models in ATC communication and can be considered as one of the metrics for evaluating the quality of ATC speech.

A lightweight speech recognition method with target-swap knowledge distillation for Mandarin air traffic control communications

Miscommunications between air traffic controllers (ATCOs) and pilots in air traffic control (ATC) may lead to catastrophic aviation accidents. Thanks to advances in speech and language processing, automatic speech recognition (ASR) is an appealing approach to prevent misunderstandings. To allow ATCOs and pilots sufficient time to respond instantly and effectively, the ASR systems for ATC must have both superior recognition performance and low transcription latency. However, most existing ASR works for ATC are primarily concerned with recognition performance while paying little attention to recognition speed, which motivates the research in this article. To address this issue, this article introduces knowledge distillation into the ASR for Mandarin ATC communications to enhance the generalization performance of the light model. Specifically, we propose a simple yet effective lightweight strategy, named Target-Swap Knowledge Distillation (TSKD), which swaps the logit output of the teacher and student models for the target class. It can mitigate the potential overconfidence of the teacher model regarding the target class and enable the student model to concentrate on the distillation of knowledge from non-target classes. Extensive experiments are conducted to demonstrate the effectiveness of the proposed TSKD in homogeneous and heterogeneous architectures. The experimental results reveal that the generated lightweight ASR model achieves a balance between recognition accuracy and transcription latency.

Lessons Learned in Transcribing 5000 h of Air Traffic Control Communications for Robust Automatic Speech Understanding

Voice communication between air traffic controllers (ATCos) and pilots is critical for ensuring safe and efficient air traffic control (ATC). The handling of these voice communications requires high levels of awareness from ATCos and can be tedious and error-prone. Recent attempts aim at integrating artificial intelligence (AI) into ATC communications in order to lessen ATCos’s workload. However, the development of data-driven AI systems for understanding of spoken ATC communications demands large-scale annotated datasets, which are currently lacking in the field. This paper explores the lessons learned from the ATCO2 project, which aimed to develop an unique platform to collect, preprocess, and transcribe large amounts of ATC audio data from airspace in real time. This paper reviews (i) robust automatic speech recognition (ASR), (ii) natural language processing, (iii) English language identification, and (iv) contextual ASR biasing with surveillance data. The pipeline developed during the ATCO2 project, along with the open-sourcing of its data, encourages research in the ATC field, while the full corpus can be purchased through ELDA. ATCO2 corpora is suitable for developing ASR systems when little or near to no ATC audio transcribed data are available. For instance, the proposed ASR system trained with ATCO2 reaches as low as 17.9% WER on public ATC datasets which is 6.6% absolute WER better than with “out-of-domain” but gold transcriptions. Finally, the release of 5000 h of ASR transcribed speech—covering more than 10 airports worldwide—is a step forward towards more robust automatic speech understanding systems for ATC communications.

Natural Language Processing (NLP) in Aviation Safety: Systematic Review of Research and Outlook into the Future

Advanced digital data-driven applications have evolved and significantly impacted the transportation sector in recent years. This systematic review examines natural language processing (NLP) approaches applied to aviation safety-related domains. The authors use Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) to conduct this review, and three databases (Web of Science, Scopus, and Transportation Research International Documentation) are screened. Academic articles from the period 2010–2022 are reviewed after applying two rounds of filtering criteria. The sub-domains, including aviation incident/accident reports analysis and air traffic control (ATC) communications, are investigated. The specific NLP approaches, related machine learning algorithms, additional causality models, and the corresponding performance are identified and summarized. In addition, the challenges and limitations of current NLP applications in aviation, such as ambiguity, limited training data, lack of multilingual support, are discussed. Finally, this review uncovers future opportunities to leverage NLP models to facilitate the safety and efficiency of the aviation system.

AKAASH: A realizable authentication, key agreement, and secure handover approach for controller-pilot data link communications

Controller-Pilot Data Link Communications (CPDLC) are rapidly replacing voice-based Air Traffic Control (ATC) communications worldwide. Being digital, CPDLC is highly resilient and bandwidth efficient, which makes it the best choice for traffic-congested airports. Although CPDLC initially seems to be a perfect solution for modern-day ATC operations, it suffers from serious security issues. For instance, eavesdropping, spoofing, man-in-the-middle, message replay, impersonation attacks, etc. Cyber attacks on the aviation communication network could be hazardous, leading to fatal aircraft incidents and causing damage to individuals, service providers, and the aviation industry. Therefore, we propose a new security model called AKAASH, enabling several paramount security services, such as efficient and robust mutual authentication, key establishment, and a secure handover approach for the CPDLC-enabled aviation communication network. We implement the approach on hardware to examine the practicality of the proposed approach and verify its computational and communication efficiency and efficacy. We investigate the robustness of AKAASH through formal (proverif) and informal security analysis. The analysis reveals that the AKAASH adheres to the CPDLC standards and can easily integrate into the CPDLC framework.

Cognitive Load Assessment of Air Traffic Controller Based on SCNN-TransE Network Using Speech Data

Due to increased air traffic flow, air traffic controllers (ATCs) operate in a state of high load or even overload for long periods of time, which can seriously affect the reliability and efficiency of controllers’ commands. Thus, the early identification of ATCs who are overworked is crucial to the maintenance of flight safety while increasing overall flight efficiency. This study uses a comprehensive comparison of existing cognitive load assessment methods combined with the characteristics of the ATC as a basis from which a method for the utilization of speech parameters to assess cognitive load is proposed. This method is ultimately selected due to the minimal interference of the collection equipment and the abundance of speech signals. The speech signal is pre-processed to generate a Mel spectrogram, which contains temporal information in addition to energy, tone, and other spatial information. Therefore, a speech cognitive load evaluation model based on a stacked convolutional neural network (CNN) and the Transformer encoder (SCNN-TransE) is proposed. The use of a CNN and the Transformer encoder allows us to extract spatial features and temporal features, respectively, from contextual information from speech data and facilitates the fusion of spatial features and temporal features into spatio-temporal features, which improves our method’s ability to capture the depth features of speech. We conduct experiments on air traffic control communication data, which show that the detection accuracy and F1 score of SCNN-TransE are better than the results from the support-vector machine (SVM), k-nearest neighbors (KNN), random forest (RF), adaptive boosting (AdaBoost), and stacked CNN parallel long short-term memory with attention (SCNN-LSTM-Attention) models, reaching values of 97.48% and 97.07%, respectively. Thus, our proposed model can realize the effective evaluation of cognitive load levels.

Satellite Attitude Determination Using ADS-B Receiver and MEMS Gyro

Automatic dependent surveillance-broadcast (ADS-B) is a very important communication and surveillance technology in air traffic control (ATC). In the future, more and more satellites will carry out ADS-B technology to perform a global coverage. In order to make full use of the resources in the satellite, this paper proposes a solution for satellite three-axis attitude determination using the ADS-B receiver. The principle of ADS-B-based attitude determination is presented first. On this basis, ADS-B-based methods are employed to solve the problem. To achieve a higher attitude determination precision, gyro is combined with the ADS-B receiver using a multiplicative extended Kalman filter (MEKF). Finally, a simulation is carried out and the result is presented.

A Wideband High-Gain Circularly-Polarized Dielectric Horn Antenna Equipped With Lamé-Axicon Stacked-Disk Lens for Remote Sensing, Air Traffic Control and Satellite Communications

A wideband high-gain circularly polarized (CP) shaped dielectric horn-lens antenna (SDHLA) operating in the frequency band between 6.7 and 18.2 GHz [fractional impedance bandwidth (FIBW) of 92.4%] with a 3-dB axial-ratio in the frequency range from 8.1 to 16.3 GHz [fractional axial-ratio bandwidth (FARBW) of 67.2%], is presented. The antenna, composed of a suitably shaped dielectric horn, integrated with a super-ellipsoidal-axicon dielectric lens made out of stacked thin dielectric disks, is mounted on a printed circuit board (PCB) where a broadband microstrip line terminated with a radial stub is used to excite a S-shaped slot through which the circular polarization is achieved. Parameterized 3D Lamé curves describe the optimal geometries of horn and lens profiles. The antenna features a peak realized gain exceeding 13.1 dBi that is beneficial in a variety of applications, such as digital video broadcasting (DVB), remote sensing, weather monitoring, satellite communications, and air traffic control. The full-wave electromagnetic solver CST Studio Suite™, based on a locally conformal finite integration technique (FIT), was employed to design and characterize the antenna. The antenna characteristics estimated by FIT were found to be in good agreement with the experimental measurements performed on an antenna prototype.

Polarization-controllable and angle-insensitive multiband Yagi-Uda-shaped metamaterial absorber in the microwave regime

This paper reports a multiband Yagi-Uda shaped metamaterial absorber (YUMA) operating in X- and Ku-band of the microwave regime with the added functionalities of miniaturization, polarization controllability and wide incidence angle stability. The proposed YUMA shows three distinctive near-unity absorption peaks corresponding to 10.64 GHz, 12.08 GHz, and 14.09 GHz frequencies. The YUMA was analyzed under different oblique incidence angles for transverse electric (TE)-mode and different rotation angles of the top metasurface. The results showed that the proposed YUMA possesses multifunctional characteristics such as polarization controllability, and wide incidence angle stability. The comparison of simulated and measured results further demonstrates that the proposed absorber can be a potential candidate in polarization detection systems and transmissive polarizers. The proposed YUMA operating in the X- and Ku-band can have potential uses in several other applications, such as air traffic control, weather monitoring, military radar, and satellite communication.

Automatic Speech Recognition for Air Traffic Control Communications

A significant fraction of communications between air traffic controllers and pilots is through speech, via radio channels. Automatic transcription of air traffic control (ATC) communications has the potential to improve system safety, operational performance, and conformance monitoring, and to enhance air traffic controller training. We present an automatic speech recognition model tailored to the ATC domain that can transcribe ATC voice to text. The transcribed text is used to extract operational information such as call-sign and runway number. The models are based on recent improvements in machine learning techniques for speech recognition and natural language processing. We evaluate the performance of the model on diverse datasets.

Aeronautical Meteorology in Aeronautical Language and in Aviation Language: a hybrid field?

Although Aeronautical Meteorology language is not generally regarded as standard communication between air traffic controllers and pilots, it plays an important role in Air Traffic Control (ATC) communication since it comprises phraseology and plain language used to communicate weather phenomena which interfere in aviation operations. Then, this paper focuses on the meteorology terminology used by Brazilian experts and discusses whether Aeronautical Meteorology is a hybrid field. Based on the theory of lexical semantics for terminology proposed by L’Homme (2020), the syntactic and semantic properties of a small set of Portuguese terms were analyzed in two separate textual corpora, i.e. a corpus representative of Aviation language and a corpus representative of Aeronautical language. For that, the combinatorics of terms were examined by means of a concordancing tool and were categorized by means of semantic labels. Quantification and comparison of the results obtained seem to suggest that the behavior of the terms in the two corpora share a fair amount of similarities.

Preliminary Exploration of the Reliability of Civil Aviation ATC Communication Network

In this paper, the factors affecting the reliability of the Air Traffic Control (ATC) communication system in operation are analyzed. From the perspective of the ATC communication network characteristics, the ideas and methods for reliability research on the ATC communication system are proposed. At the same time, the civil aviation communication network is taken as an example to explore the construction of the backup system for the communication network, the steps of evaluation methods, and the reliability management ideas.

Implementation of Automatic Aircraft Tracking with RTL-SDR

To improve the efficiency, safety, and capacity of air space system, an Automatic Dependent Surveillance-Broadcast (ADS-B) is one of the popular technologies used in air traffic surveillance. The ADS-B uses 1090 MHz band. ADS-B is complemented by existing radar-based technologies to locate aircraft. The coexistence of radar systems and ADS-B is a key system to detect and resolve conflicts in the Next Generation Air Transportation System (NGATS). But, the major disadvantage of ADS-B is its implementation complexity and increase in cost without user-friendly. This paper focuses to reduce the complexity and cost of ADS-B system implementation in MATLAB with the help of Software Defined Radio (SDR). SDR is user-friendly and easy to handle aircraft information without increasing the cost. The ADS-B system implemented with SDR can receive the multiple numbers of aircraft information such as altitude, latitude, longitude, speed, and direction in real-time. Usage of SDR maximizes the information coverage with reliability and can achieve timely communication in Air Traffic Control (ATC) networks.

On the Applicability of Satellite-Based Air Traffic Control Communication for Security

As air traffic control communication moves toward digital systems, there is an emerging trend toward supplementing or even fully substituting the traditional air-ground link in favor of communication between aircraft and satellites. In this article, we analyze coverage and security against wireless attacks of the novel satellite-based version of the Automatic Dependent Surveillance-Broadcast (ADS-B) technology. We compare it to the widely deployed terrestrial ADS-B system, which is known to be insecure and is inherently unable to provide coverage in some parts of the global airspace, such as oceans and polar regions. Our analysis shows that satellites can provide vast advantages in such non-surveillance areas. However, they are as fundamentally insecure as terrestrial ADS-B.

Air traffic control communication (ATCC) speech corpora and their use for ASR and TTS development

The paper introduces the motivation for creating dedicated speech corpora of air traffic control communication, describes in detail the process of preparation of corpora for both automatic speech recognition and text-to-speech synthesis, presents an illustrative example of speech recognition system developed using the automatic speech recognition corpora and finally describes the technical aspects of the data and the distribution channel.

Multiple-Path Erasure Coding for Future Air Traffic Control Communications

The air traffic control data communications performance is measured using the International Civil Aviation Organization’s Required Communication Performance metric. The metric’s values proposed by Eurocontrol and the Federal Aviation Administration to support the future data-centric air traffic control communications will only be achievable using a new, air–ground data link with low latency and low loss. In this Paper, we propose using erasure coding to generate redundancy and transmitting over multiple links, each with higher latency and/or higher loss than the single link. We propose a model to calculate the expected performance using multiple links and erasure coding based on the different links characteristics, the coding rate, and the encoded packet distribution over the links. Then, we present the results of using the model to calculate the characteristics of multiple new air–ground data links that support the requirements of the future air traffic control communications, and we compare them with the results of a single link.

Real-time Controlling Dynamics Sensing in Air Traffic System.

In order to obtain real-time controlling dynamics in air traffic system, a framework is proposed to introduce and process air traffic control (ATC) speech via radiotelephony communication. An automatic speech recognition (ASR) and controlling instruction understanding (CIU)-based pipeline is designed to convert the ATC speech into ATC related elements, i.e., controlling intent and parameters. A correction procedure is also proposed to improve the reliability of the information obtained by the proposed framework. In the ASR model, acoustic model (AM), pronunciation model (PM), and phoneme- and word-based language model (LM) are proposed to unify multilingual ASR into one model. In this work, based on their tasks, the AM and PM are defined as speech recognition and machine translation problems respectively. Two-dimensional convolution and average-pooling layers are designed to solve special challenges of ASR in ATC. An encoder–decoder architecture-based neural network is proposed to translate phoneme labels into word labels, which achieves the purpose of ASR. In the CIU model, a recurrent neural network-based joint model is proposed to detect the controlling intent and label the controlling parameters, in which the two tasks are solved in one network to enhance the performance with each other based on ATC communication rules. The ATC speech is now converted into ATC related elements by the proposed ASR and CIU model. To further improve the accuracy of the sensing framework, a correction procedure is proposed to revise minor mistakes in ASR decoding results based on the flight information, such as flight plan, ADS-B. The proposed models are trained using real operating data and applied to a civil aviation airport in China to evaluate their performance. Experimental results show that the proposed framework can obtain real-time controlling dynamics with high performance, only 4% word-error rate. Meanwhile, the decoding efficiency can also meet the requirement of real-time applications, i.e., an average 0.147 real time factor. With the proposed framework and obtained traffic dynamics, current ATC applications can be accomplished with higher accuracy. In addition, the proposed ASR pipeline has high reusability, which allows us to apply it to other controlling scenes and languages with minor changes.

Designing the Air–Ground Data Links for Future Air Traffic Control Communications

The future air traffic management in Europe and the USA is being defined by the SESAR and NextGen programs, respectively. In the mid-2020s, air-ground air traffic control communications will be primarily data-centric as opposed to current voice-centric communications. The International Civilian Aviation Organization has proposed the required communication performance (RCP) metric to define the requirements to support the new data communication services. In this paper, we propose a model to calculate the expected performance using the RCP metric based on the air-ground data link characteristics. Then, we present the results of using the model to obtain the characteristics that an air-ground data link must have to support the future ATC communication requirements proposed by Eurocontrol and the Federal Aviation Administration.

Air traffic communications in routine and emergency contexts: A case study of Flight 1549 ‘miracle on the Hudson’

This paper is a conversation analytic investigation of Air Traffic Control (ATC) communications with U.S. Air Flight 1549 and other flights before, during, and after a critical emergency in which the plane (safely) landed in the Hudson River. While foundational conversation analytic research on air traffic communications has already been done, this method has not yet been systematically applied to air traffic communications during actual emergencies. This project will therefore fill a gap in previous research by analyzing ATC/plane interactions during an actual emergency and investigating whether routinized procedures alone are the most effective when emergency situations occur. I will show how routine interactional conventions in this work setting (e.g., the use of scripted talk and ‘positional’ grammar) help participants to maintain the safe flow of air traffic and to accommodate emergencies when they occur. I will show that during the critical emergency the ATCO and the pilot of Flight 1549 switched from a routinized (scripted) form of interaction to a conversational form of interaction, and at times to a ‘hybrid’ format which combined elements of routine ATC talk with elements of the speech exchange system of ordinary conversation.

Особенности профессиональной коммуникации авиадиспетчеров как основа для составления упражнений по профессионально-ориентированному английскому языку

Особенности профессиональной коммуникации авиадиспетчеров как основа для составления упражнений по профессионально-ориентированному английскому языку