A5084509592- Speech Recognition and Synthesis
- Speech and dialogue systems
- Speech and Audio Processing
- Air Traffic Management and Optimization
- Human-Automation Interaction and Safety
- Natural Language Processing Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Maritime Navigation and Safety
- Risk and Safety Analysis
- Aerospace and Aviation Technology
- Aerospace Engineering and Applications
- Advanced SAR Imaging Techniques
- Advanced Aircraft Design and Technologies
- Music and Audio Processing
- Robotics and Automated Systems
- Transportation Systems and Safety
- Digital Innovation in Industries
- Quality and Safety in Healthcare
- Distributed systems and fault tolerance
- Corporate Social Responsibility and Sustainability
- Network Traffic and Congestion Control
- Healthcare Technology and Patient Monitoring
- Spacecraft Dynamics and Control
- Real-time simulation and control systems
- Libraries and Information Services
Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)
2015-2025
Recent work on self-supervised pre-training focus leveraging large-scale unlabeled speech data to build robust end-to-end (E2E) acoustic models (AM) that can be later fine-tuned downstream tasks e.g., automatic recognition (ASR). Yet, few works investigated the impact performance when properties substantially differ between and fine-tuning phases, termed domain shift. We target this scenario by analyzing robustness of Wav2Vec 2.0 XLS-R ASR for a completely unseen domain, air traffic control...
In this paper we propose a novel virtual simulation-pilot engine for speeding up air traffic controller (ATCo) training by integrating different state-of-the-art artificial intelligence (AI)-based tools. The receives spoken communications from ATCo trainees, and it performs automatic speech recognition understanding. Thus, goes beyond only transcribing the communication can also understand its meaning. output is subsequently sent to response generator system, which resembles read-back that...
Advancements in Automatic Speech Recognition (ASR) technology is exemplified by ubiquitous voice assistants such as Siri and Alexa. Researchers have been exploring the application of ASR for Air Traffic Management (ATM) systems. Initial prototypes utilized to pre-fill aircraft radar labels achieved a technological readiness level before industrialization (TRL6). However, accurately recognizing infrequently used but highly informative domain-specific vocabulary still an issue. This includes...
While traffic levels are predicted to rise, nearly all European air navigation service providers suffer from staff shortages. In most cases, two controllers deployed control one airspace sector. Enabling the deployment of controller per sector could be a solution shortage problems. For this Single-Controller Operation (SCO) concept, demonstrator with integrated support tools based on advanced information technology was developed. These partially automate some tasks allow work off same amount...
Air Navigation Service Providers (ANSPs) replace paper flight strips through different digital solutions. The instructed commands from an air traffic controller (ATCos) are then available in computer readable form. However, those systems require manual inputs, i.e. ATCos' workload increases. Active Listening Assistant (AcListant®) project has shown that Based Speech Recognition (ABSR) is a potential solution to reduce this additional workload. the development of ABSR application for specific...
The information air traffic controllers (ATCos) communicate via radio telephony is valuable for digital assistants to provide additional safety. Yet, ATCos have enter this manually. Assistant-based speech recognition (ABSR) has proven be a lightweight technology that automatically extracts and successfully feeds the content of ATC communication into systems without human effort. This article explains how ABSR can integrated an advanced surface movement guidance control system (A-SMGCS)....
In the H2020 project “Satellite-borne and INsitu Observations to Predict The Initiation of Convection for ATM” (SINOPTICA), an air traffic controller support system was extended organize approaching even under severe weather conditions. During runtime, days with extreme events in Po Valley were analyzed, arrival manager a module 4D diversion trajectory calculation, two display variants conditions primary developed, airport Milano Malpensa modelled simulation. On meteorological side, three...
As researchers around the globe develop applications for use of Automatic Speech Recognition and Understanding (ASRU) in Air Traffic Management (ATM) domain, Control (ATC) language ontologies will play a critical role enabling research collaboration. The MITRE Corporation (MITRE) German Aerospace Center (DLR), having independently developed ATC specific applications, recently compared these to identify opportunities improvement harmonization. This paper extends topic two ways. First, this...
Automatic Speech Recognition (ASR) has recently proved to be a useful tool reduce the workload of air traffic controllers leading significant gains in operational efficiency.Air Traffic Control (ATC) systems operation rooms around world generate large amounts untranscribed speech and radar data each day, which can utilized build improve ASR models.In this paper, we propose an iterative approach that utilizes increasing incrementally necessary models for ATC area.Our uses semi-supervised...
Nowadays Arrival Managers (AMAN) are available to produce efficient inbound traffic sequences and create guidance advisories for optimized approaches. Information about deviations from the planned sequence is exchanged between controller pilot via radio communication. The AMAN only able derive these radar data. Using data as single input sensor, however, results in adaptation delays of 30 seconds more - even worse, controllers' intent still missing. AcListant® (Active Listening Assistant)...
Sophisticated Automatic Speech Recognition (ASR) technologies have become increasingly popular and are widely used in all domains over the years. Systems like Google Assistant, Siri®, Alexa® integrated into our day-to-day lives. These systems offer a wide range of possible applications just by understanding human speech. However, Air Traffic Control (ATC) domain, even most advanced simulators can partially replace expensive pseudo-pilots. In spite having standardized ATC phraseology, it is...
Automatic speech recognition and understanding (ASRU) for air traffic control (ATC) has been investigated in different ATC environments applications. The objective of this study was to quantify the effect ASRU support controllers (ATCos) radar label maintenance terms safety human performance. Therefore, an implemented system validated within a human-in-the-loop environment by ATCos traffic-density scenarios. In baseline condition, performed entering verbally instructed commands with mouse...
Increasing digitization and automation is a widely accepted method to cope with the challenges of constantly increasing air traffic. The analogue communication traffic controllers (ATCo) pilots has been excluded so far from process. However, content this decisive importance for various systems. Although Assistant Based Speech Recognition (ABSR) recently significantly improved recognition performance and, therefore, enables ATCo-pilot-communication, its adaptation other airports critical...
This paper presents an approach for incorporating situational context information into on-line Automatic Speech Recognition (ASR) component of Air Traffic Control (ATC) assistance system to improve recognition performance. Context is treated as prior reduce the search space recognition. It integrated in ASR pipeline by continually updating network. achieved automatically adapting underlying grammar whenever new knowledge becomes available. The context-dependent network then re-created and...
Adverse weather conditions can have major impacts on air traffic and its control (ATC) in terms of safety capacity. However, today's ATC situation data displays hardly contain any information. Controllers only manually react external forecasts or status reports to re-plan the aircraft flight paths. The project "Meteorology for Air Traffic Management" (MET4ATM) uses nowcast forecast re-routing calculations visualization radar display. If our Arrival Manager (AMAN) detects that a planned...
Since years it is known that radio communication used by ATC can easily be intruded and therefore subject to recurrent attacks. Nevertheless the voice between pilots air traffic controllers still most flexible efficient medium especially in a busy environment, non-standard situations or simply when exchanging air-ground messages plain language needed. As vulnerability seems not dominant compared number of crucial damages, basic important method within aeronautical mobile service. This...
Assistant Based Speech Recognition (ABSR) systems for air traffic control radiotelephony communication have shown their potential to reduce controllers’ (ATCos) workload. Related research activities mainly focused on utterances approach and en-route traffic. This is one of the first investigations how ABSR could support ATCos in a tower environment. Ten from Lithuania Austria participated human-in-the-loop simulation validate within prototypic multiple remote controller working position. The...
(1) Functionality benefits of ABSR based AMAN on trajectory conformance and sequence stability (2) positively influences ATCo workload (3) supports more effectively than without any sensor or updated with mouse (4) perceived regarding conventional method operation is nearly the same level