PhD or Postdoc positon in the field of ASR & NLP for structured selection interviews

There is an opening at Idiap Research Institute for a project on speech recognition and natural language processing in the context of structured selection interviews (job interviews). The project is a collaboration between psychology departments at the universities of Neuchâtel and Lausanne, and the speech and audio processing group at Idiap.

The research will involve study of deep hierarchical architectures for semantic inference. Building on state of the art approaches to speech and language processing, the pipeline is likely to make use of pre-trained self supervised models (e.g., wav2vec2, BERT). The open questions include how to customise such approaches to structured selection interviews, in particular the role of storytelling.

There will be ample opportunity for research in the component technologies, which are all currently pertinent in the general machine learning landscape. In particular, we expect to make advances in the technological interfaces between component technologies, and in the humanist interfaces between the machine learning practitioners and social scientists.

The position would fund a PhD student for four years, or a post-doctoral researcher for perhaps two years. The ideal PhD candidate should have a master (or equivalent) degree in engineering, computer science, physics or applied mathematics. In the case of a post-doctoral researcher, a doctorate in a similar subject. Depending on experience, a background in psychology may be appropriate. A good background in programming (C/C++, Python, scripting languages) is essential; practical engineering skills in general will be particularly appreciated since the work of our collaborators will be dependent on the output of our part of the project.

In order to balance the group, we especially encourage female applicants. However, all applications will be judged on merit.

The candidate will be located at Idiap. In the case of a PhD student, the candidate will be registered at EPFL, or possibly one of the partner institutions. In any case, we expect some time to be spent at our collaborators' locations, especially during data collection and annotation.

The position is available immediately; interviews will commence as soon as applications are received.