Article
Computer Science, Artificial Intelligence
Yi Lin, YuanKai Wu, Dongyue Guo, Pan Zhang, Changyu Yin, Bo Yang, Jianwei Zhang
Summary: In this study, a deep learning-based APA framework is proposed to assist ATCO training, with a focus on PRG and TTS models. Experimental results show that the APA framework can replace human pilots in real-time during simulation training. The virtual training mode offered by the APA framework and the system solves the dilemma of physical attendance and improves equipment utilization capacity for ATCO training.
IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS
(2021)
Article
Engineering, Aerospace
Raquel Garcia, Juan Albarran, Adrian Fabio, Fernando Celorrio, Carlos Pinto de Oliveira, Cristina Barcena
Summary: In the air traffic management environment, air traffic controllers and flight crews communicate via voice using speech recognition to improve situational awareness and safety. This paper presents the work being done to develop ASR models for callsign recognition and highlights the need for partial recognition and improved phonetization to enhance recognition rates.
Article
Engineering, Aerospace
Nils Ahrenhold, Hartmut Helmke, Thorsten Muehlhausen, Oliver Ohneiser, Matthias Kleinert, Heiko Ehr, Lucas Klamert, Juan Zuluaga-Gomez
Summary: This study investigates the use of automatic speech recognition and understanding (ASRU) in air traffic control. Findings show that ASRU support can reduce workload and improve safety and human performance.
Article
Engineering, Aerospace
Juan Zuluaga-Gomez, Iuliia Nigmatulina, Amrutha Prasad, Petr Motlicek, Driss Khalil, Srikanth Madikeri, Allan Tart, Igor Szoke, Vincent Lenders, Mickael Rigault, Khalid Choukri
Summary: This paper discusses the integration of artificial intelligence into air traffic control (ATC) communications in order to lessen the workload of air traffic controllers. The lessons learned from the ATCO2 project, which developed a platform to collect, preprocess, and transcribe real-time ATC audio data, are explored. The paper reviews various techniques, including automatic speech recognition (ASR), natural language processing, English language identification, and contextual ASR biasing with surveillance data. The release of the ATCO2 corpora, along with the open-sourcing of its data, encourages research in the field and allows the development of ASR systems when little to no ATC audio transcribed data is available. The proposed ASR system trained with ATCO2 achieves a lower word error rate (WER) compared to out-of-domain transcriptions, indicating its effectiveness.
Article
Engineering, Aerospace
Matthias Kleinert, Oliver Ohneiser, Hartmut Helmke, Shruthi Shetty, Heiko Ehr, Mathias Maier, Susanne Schacht, Hanno Wiese
Summary: This article explains how assistant-based speech recognition (ABSR) technology can be integrated into an advanced surface movement guidance and control system (A-SMGCS) to reduce controllers' workload and improve safety and overall performance. The integration of A-SMGCS and ABSR improves the command recognition rate by more than 15%, with a recognition rate of 91.8% for commands and 97.4% for callsigns, effectively reducing controllers' workload and enhancing safety and overall performance.
Article
Engineering, Civil
Sandeep Badrinath, Hamsa Balakrishnan
Summary: Automatic transcription of air traffic control (ATC) communications has the potential to improve system safety, operational performance, and conformance monitoring. A tailored automatic speech recognition model has been developed to transcribe ATC voice to text and extract operational information. The model is based on recent advancements in machine learning techniques and has been evaluated on diverse datasets.
TRANSPORTATION RESEARCH RECORD
(2022)
Review
Engineering, Aerospace
Yi Lin
Summary: This paper provides a comprehensive review on spoken instruction understanding (SIU) in the ATC domain, covering challenges, techniques, and applications. It discusses the full pipeline for achieving the SIU task, analyzes technique challenges specific to ATC tasks, categorizes common techniques for SIU tasks, and reviews extensive works in the ATC domain. Future research topics are also prospected to contribute to the research community.
Article
Engineering, Aerospace
Shuo Chen, Hartmut Helmke, Robert M. M. Tarakan, Oliver Ohneiser, Hunter Kopald, Matthias Kleinert
Summary: As the use of Automatic Speech Recognition and Understanding (ASRU) in Air Traffic Management (ATM) is developed worldwide, the importance of Air Traffic Control (ATC) language ontologies in facilitating research collaboration becomes evident. This paper extends the topic by discussing the specific ways in which ontologies enable the sharing and collaboration of data, models, algorithms, metrics, and applications in the ATM domain. Additionally, a comparative analysis of word frequencies in ATC speech between the United States and Europe highlights the need for region-specific models due to differences in underlying corpus data.
Article
Engineering, Aerospace
Adan Ernesto Vela, William Singhose, Karen Feigh, John-Paul Clarke, Eric Feron
Summary: This paper examines the potential workload implications of introducing advisory conflict-detection and resolution tools by evaluating how the underlying protocol of a conflict-resolution tool affects the controller taskload. The research shows significant flexibility in the design of conflict-resolution algorithms supporting an advisory system.
CHINESE JOURNAL OF AERONAUTICS
(2021)
Article
Computer Science, Artificial Intelligence
Jianwei Zhang, Pan Zhang, Dongyue Guo, Yang Zhou, Yuankai Wu, Bo Yang, Yi Lin
Summary: In order to eliminate the need for human pseudo-pilots in air traffic controller training, a multi-task framework with a copy mechanism is proposed to automatically generate a repetition instruction. The framework uses a sequence-to-sequence architecture optimized through multi-task learning, achieving improved efficiency and accuracy in air traffic control.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Engineering, Aerospace
Yi Lin, Min Ruan, Kunjie Cai, Dan LI, Ziqiang Zeng, Fan LI, Bo Yang
Summary: The primary focus of this work is to identify potential technical risks of AI-driven operations for air traffic safety monitoring through a case study and user experience evaluation. The results from the case study and user experience evaluation show that the proposed solution is promising for improving traffic safety and reducing workload by detecting potential risks in advance. However, the AI-driven techniques and system should be enhanced to eliminate possible distractions to air traffic controller attention. Various strategies and approaches are discussed to advance the proposed solution to industrial practices.
CHINESE JOURNAL OF AERONAUTICS
(2023)
Article
Engineering, Aerospace
Maria Zamarreno Suarez, Rosa Maria Arnaldo Valdes, Francisco Perez Moreno, Raquel Delgado-Aguilera Jurado, Patricia Maria Lopez de Frutos, Victor Fernando Gomez Comendador
Summary: The study of human factors in aviation contributes significantly to safety, especially with the use of real-time simulations. The CRITERIA project aims to establish capacity models and investigate the influence of air traffic control events on the workload of air traffic controllers. This paper presents a methodology for defining taskload during simulations and provides recommendations for future research.
Article
Mathematics
Stefan Dascalu, Florentina Hristea
Summary: Hate Speech is a frequently occurring problem on the internet, and various countries are developing regulations to combat this type of speech. However, current research on Hate Speech detection lacks a benchmarking system to compare the performance of different methods in predicting various types of text. This paper provides a standardized testing approach for Hate Speech detection by evaluating the performance of different models.
Article
Engineering, Aerospace
Oliver Ohneiser, Hartmut Helmke, Shruthi Shetty, Matthias Kleinert, Heiko Ehr, Sebastian Schier-Morgenthal, Saeed Sarfjoo, Petr Motlicek, Sarunas Murauskas, Tomas Pagirys, Haris Usanovic, Mirta Mestrovic, Aneta Cerna
Summary: Assistant Based Speech Recognition (ABSR) systems have the potential to reduce air traffic controllers' workload in air traffic control radiotelephony communication. This study investigates how ABSR could support air traffic controllers in a tower environment. The results show that ABSR system, with a command recognition rate of 82.9% and a callsign recognition rate of 94.2%, can reduce workload and improve usability.
Article
Engineering, Multidisciplinary
Yanjun Wang, Liwei Wang, Siyuan Lin, Wei Cong, Jianfei Xue, Washington Ochieng
Summary: Eye movement is a crucial indicator of information-seeking behavior and cognitive strategy for decision-making. The study shows that working experience significantly impacts eye movement patterns in air traffic controllers, with experienced controllers utilizing more efficient search strategies compared to novices.
Article
Transportation
Oliver Ohneiser, Hartmut Helmke, Shruthi Shetty, Matthias Kleinert, Heiko Ehr, Sarunas Murauskas, Tomas Pagirys
Summary: Research has shown that automatic speech recognition systems can significantly reduce air traffic controllers' workload and increase air traffic capacity, but they require accurate command hypotheses and extractions to achieve the desired performance.
JOURNAL OF AIR TRANSPORT MANAGEMENT
(2021)
Article
Computer Science, Information Systems
Qingran Zhan, Xiang Xie, Chenguang Hu, Juan Zuluaga-Gomez, Jing Wang, Haobo Cheng
Summary: This paper investigates the extraction of reliable AFs using a DANN for cross-lingual speech recognition. By training AFs detectors in source languages and transferring phonological knowledge to the target language, along with the fusion of acoustic features and cross-lingual AFs using multi-stream techniques, improved performance is achieved. The experiments show that using CNN with domain-adversarial learning and the MHA-based multi-stream approach yield significant improvements in performance compared to other methods, especially when considering low-resource languages.
Article
Engineering, Aerospace
Nils Ahrenhold, Hartmut Helmke, Thorsten Muehlhausen, Oliver Ohneiser, Matthias Kleinert, Heiko Ehr, Lucas Klamert, Juan Zuluaga-Gomez
Summary: This study investigates the use of automatic speech recognition and understanding (ASRU) in air traffic control. Findings show that ASRU support can reduce workload and improve safety and human performance.
Review
Engineering, Chemical
J. Zuluaga-Gomez, P. Bonaveri, D. Zuluaga, C. Alvarez-Pena, N. Ramirez-Ortiz
DESALINATION AND WATER TREATMENT
(2020)