Short description

In some cases recodings have to be made without the possibility of professial supervision. To make the recording procedure failure safe we have designed a recording device that is more or less self-explanatory. Given the learning from the field we wanted to improve the recoding device to also include acoustic scene classification so it can give feedback to the users to ensure optimal recording conditions.

Tasks (depending on specific project):

• Review of literature and potential algorithms
• Choose the most promising algorithm.
• Run the algorithms with the given data and design evaluation apprach
• Implement the most promising approach (Masters’s thesis)
• Evaluate the chosen approach(es)
• Build the device
• Documentation

Your Profile/Prerequisites

• Motivation and interest in the topic
• Background in Speech Signal Processing
  (e.g. completed Speech Communication 1)
• Experience with either Matlab, Python or Julia
• Team work is very welcome

Contact:

Martin Hagmüller (hagmueller@tugraz.at or 0316/873 4377)