Master thesis - emotion recognition in public Transportation

Job-ID: T-TV Vehicle Solutions & Automated Driving-22088

Master thesis - emotion recognition in public Transportation

______

Students  —  Thesis

Gifhorn, München

This challenge awaits you:

Are you a master’s student in engineering, computer science, or a related field with interest in Deep Learning and audio processing? We have a fantastic opportunity for a talented and motivated student to join our team and work with us on emotion recognition models.  This position is offering a research task in combination with a master’s thesis in one the mentioned fields. We are seeking a highly motivated and innovative individual who can bring their expertise to drive our research forward.

Your Tasks:

• Conduct research in speech emotion detection and analysis, exploring time and frequency domain features, as well as deep learning techniques.

• Collect and annotate data and ensure the quality and integrity of datasets.

• Develop and refine algorithms and models for real-time emotion recognition, with a focus on robustness and accuracy.

• Collaborate with cross-functional teams, to develop multi-modal emotion detection solutions.

Necessary Skills:

• Currently pursuing a master’s degree in engineering, computer science, automotive, or a related field with a focus on speech or image processing, and machine learning.

• Familiarity with audio and speech signal processing, feature extraction, and time-frequency analysis.

• Strong Python skills.

• Fluency in English or German.

• Experience with deep learning frameworks (e.g., PyTorch, TensorFlow, Keras).

• Familiarity with collaborative software development tools (e.g., git).

Desired Skills:

• Proficiency in integrating multiple data modalities, such as audio and video.

• Knowledge of statistical methods for analyzing and interpreting the relationships between features and emotional states

• Skill in fine-tuning model hyperparameters for optimal performance, such as adjusting learning rates, batch sizes, filters and epochs.

• Familiarity with classification and regression models.

Das spricht für uns:

Als Student:in arbeitest du bei IAV nicht irgendwo, sondern mittendrin. In echten Projekten. An spannenden Zukunftsaufgaben. Voll integriert und im Schulterschluss mit IAV-Expert:innen. Viel Verantwortung und gleichzeitig viel Freiraum, um Uni und Arbeit zusammen zu bringen: So entstehen beste Perspektiven für deine berufliche Entwicklung. Bei attraktiver Vergütung nach unserem Haustarifvertrag.

Uns sind Vielfalt und Chancengleichheit wichtig. Für uns zählt der Mensch mit seiner Persönlichkeit und seinen Stärken.