Working student / Master's thesis – AI-based audio processing / DCASE-Challenge 2025 in Gifhorn bei IAV GmbH

With new developments in the field of AI and machine learning, the high-performance methods based on these are increasingly being used for the automatic processing, analysis and generation of audio data. This enables machines to extract information from audio signals, analogous to a person who continuously perceives information in their acoustic environment. Among the many possible applications, acoustic event or anomaly detection methods can be used, for example, to identify disturbing noises in vehicles, detect glass breakage events in urban environments or classify animal noises. Acoustic event detection and applications of similar methods (tasks) are published annually in the international DCASE Challenge as a competition together with publicly available data sets. Each task requires participants to master a specific method, e.g. few-shot learning or anomaly detection. By participating in one or more tasks of the DCASE challenge, IAV aims to expand existing skills and develop customer-relevant methods. At the same time, you will have the opportunity to work on an exciting topic of current research as part of a Master's thesis.

• You select procedures and data for a task
• You train and optimize AI-based models
• You submit the model results for a task as part of the DCASE Challenge 2025
• You prepare a technical report on the method used and the results submitted

• Ongoing studies in the field of computer science, mechatronics, electrical engineering or a comparable technical or scientific degree program
• Programming experience in at least one high-level programming language
• Very good written and spoken English skills
• Good knowledge of German (level B2 or higher)

• Experience or interest in the following programming languages / frameworks / tools: Python, Tensorflow, Keras, PyTorch, Kubeflow
• Experience with or interest in machine learning, neural networks or pattern recognition
• Independent and structured way of working
• Willingness to learn, strong initiative as well as communication and teamwork skills

Remuneration is based on our collective wage and salary agreement. The current hourly rate for this position is EUR 17.52. From February 2025, the hourly rate for this position will be EUR 18.10. The Master's thesis is remunerated with a monthly salary of EUR 979.00. From February 2025, the monthly salary for this position will be EUR 1,012.00.