Master-Thesis (m/f/d) – Lightweight Environment Classification for hearables

Abstract:

Adaptive transparence/noise cancellation is an emerging feature that is becoming available on hearables (such as the AirPods in iOS 17). While one could solve this problem via a soundscape adaptation approach, a more computationally simple method might be to classify the current environment and then based on the classification define whether ANC/Transparency/Or neither should be active – this could even be user defined.

The main part of this task would be based on the low-complexity acoustic scene classification problem presented at DCASE [1]], where a minimal footprint ML approach would be defined for environment classification. The study could then consider the creation of a decision tree based on user preference tests (or user defined protocol) for when ANC/Transparency/Neither should be active.

[1] https://dcase.community/challenge2023/task-low-complexity-acoustic-scene-classification

• Flexible working hours
• Open and friendly team work
• Networking with scientists
• Active contribution in applied research
• Interesting an innovative projects

Your start date and weekly working hours will be determined individually with you. After your studies, there are attractive opportunities to join the institute on a full time or part time basis.

We would be happy to offer you the opportunity to write a master's thesis in cooperation with us in the above-mentioned subject area. The thesis will be assigned and carried out in accordance with the rules of your university. For this reason, please discuss the thesis with a professor who can advise you over the course of the project. 

We value and promote the diversity of our employees' skills and therefore welcome all applications - regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity.