Short Description

Learning to speak again without a larynx is a challenging task. Usually speech produced by the bionic voice is more difficult to understand than using healty voice. Therefore it is critical, that the speaker learns to speak as intelligible as possible.

In order to monitor the intelligibility of EL speech a tool should be developed to monitor EL speech. This tool should work in real-time and using e.g. SNR or ASR as quality measure for EL speech should be implemented. Alternatively visual feedback by showing a target spectrum for different sounds.

Your Tasks

• Design of a Training Tool for speaking without a larynx
• GUI programming
• Documentation

Your Profile

• Motivation and interest in the topic
• Background in speech signal processing
• Background in either Matlab, Python or Julia

Contact

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