Spiking neural architectures for speech prosody

In the context of a new Swiss NSF grant, we seek a PhD student to work on neural architectures for speech technology. At the outset, we expect the work to involve spiking neural networks, and to be applied to synthesis of speech prosody.

The research will build on work done recently at Idiap on creating tools for physiologically plausible modelling of speech. The current "toolbox" contains rudimentary muscle models and means to drive these using conventional (deep) neural networks. The main focus of the work will involve use of spiking neural networks such as the "integrate and fire" type that is broadly representative of those found in biological systems. Whilst we have focused so far on prosody (actually intonation), the application is open ended; the focus is on the neural modelling. A key problem to be solved will be that of training of the spiking networks, especially with the recurrence that is usual in such networks. We hope to be able to train and use spiking networks as easily as conventional backpropagation networks, and to shed light on current understanding of how biological spiking networks learn (e.g., via spike timing-dependent plasticity).

The ideal Ph.D student should have a master (or equivalent) degree in engineering, computer science, or applied mathematics. Graduates of neuroscience programs would also be well qualified. S/he should have a good background in mathematics, statistics, and programming (C/C++, Python, scripting languages). In order to balance the group, we especially encourage female applicants. However, all applications will be judged on merit.

The position is available from November 2019. Selection will commence at the end of April 2019 and continue until the post is filled.

To apply, please go to our online recruitment system: Spiking neural architectures for speech prosody