Techn. Fakultät Willkommen am Institut für Informatik FAU-Logo

Christian Bergler M. Eng.

Researcher in the Speech Processing and Understanding (SAGI) group at the Pattern Recognition Lab of the Friedrich-Alexander-Universität Erlangen-Nürnberg

Visions are not enough for an engineer
Speech Recognition within the Air Traffic Control (ATC) Domain
Dynamic Adaption of Stochastical Language Models based on additional contextual Domain Knowledge
Air Traffic Situation in Germany, Tuesday, 10th of April 2018, 16:00 o'clock


The daily and worldwide air traffic in conjunction with the variety of aircraft specific flight scenarios, leads to an enormous communication effort between the pilots and the responsible air traffic controllers.


Considering the dimension of worldwide air traffic, the strict requirements with regards to safety, language barriers between the controllers and pilots (non-native problems), bad signal qualities as well as the huge responsibility of an air traffic controller regarding his/her airspace, it is very important to provide a control/support mechanism like speech recognition in order to make the air traffic more safe.


My research focus on the dynamic adaption of stochastic language models based on additional contextual domain knowledge within the field of Air Traffic Control (ATC).


The core idea is the extraction and use of situation-specific domain context knowledge (e.g. airport design, flight plans, radar information, weather conditions, controller command history, etc.) to dynamically adapt/update the language model for each recognition run in order to match the current flight situation best.


The main goal is to support the controller-pilot communication process via a robust Automatic Speech Recognition (ASR) system to avoid misunderstandings/misinterpretations within the whole communication chain. Furthermore such ASR technologies should support the air traffic controllers during their daily work to reduce the personal workload.

Deep Learning Applied to Animal Linguistics (DeepAL Project)
Analysis of Underwater Audio Recordings of Marine Animals (Killer Whales)
Group (family) of Orcas during DeepAL Expedition 2017


For marine biologists, the interpretation and understanding of underwater audio recordings is essential. Based on such recordings, possible conclusions about behavior, communication and social interactions of marine animals can be made.

Despite a large number of biological studies on the subject of orca vocalizations, it is still difficult to recognize a structure or semantic significance of the orca signals in order to be able to derive any patterns of behavior.


Due to a lack of  techniques and computational tools, hundreds of hours of underwater recordings are still listened to by marine biologists in order to detect potential orca vocalizations. In a post process these identified orca signals will be analyzed and categorized.


The main goal is to provide a robust method which is able to automatically detect orca calls within underwater audio recordings.


A robust detection of orca signals in connection with the associated situational video recordings and behaviour descriptions (provided by several researchers on site) can provide potential information about communication (kind of a language model) and behaviors (e.g. hunting, socializing).

Furthermore, the orca signal detection algorithm can be used in conjunction with a localization software to provide the researchers on the field a more efficient way of searching orca populations.

For more information about the DeepAL project please contact me at