Short description

The electro-larynx (EL) is a hand-held, battery-driven device. It is one possibility to regain speech for people who had to undergo an operation, where the larynx and the containing vocal folds were removed (typically due to larynx cancer). The device is held against the throat and its vibrations are transmitted through the neck. Then the patient can create speech by modulating the energy in the vocal tract.

We are in the process of designing a new speaking aid that improves significantly on the current state-of-the-art. In the scope of this project there are several small tasks that can be carried out at a student project at different levels.

• Investigate different user interfaces (e.g. joystick, Theremin, Gestures, etc.) to dynamically choose voice parameters
• Low Bandwidth extension for a personal voice amplifier for users of an electronic speaking aid
• Integrate a bluethooth sound transmission in the demonstrator system
• Lombard speech for an electronic speaking aid
• Alternative approaches for on/off control (i.e. wireless ring, gestures, breath, EMG)
• Using piezo transducer for the source signal of a bionic voice
• Compare different bone conductors as voice source (Transfer function into mouth, SPL, power requirements, …)
• Neural Voice Source Generation

Tasks (depending on specific project):

• Review of literature and potential algorithms
• Implementation of algorithms in Python and/or Julia
• Design hardware
• Choose hardware platform
• Evaluate the chosen approach(es)
• Documentation

Your Profile/Prerequisites

• Motivation and interest in the topic
• Background in Speech Signal Processing (not for bachelor project)
  (e.g. completed Speech Communication 1)
• Experience with either Matlab, Python or Julia
• For Bacherlor theses only in teams of 2-4 students

Contact:

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