Since its foundation in 1614, the University of Groningen has established an international reputation as a dynamic and innovative university offering high-quality teaching and research. Its 36,000 students are encouraged to develop their own individual talents through challenging study and career paths. The University of Groningen is an international center of knowledge: it belongs to the best research universities in Europe and is allied with prestigious partner universities and networks worldwide.
The Graduate School for the Humanities is the home to all PhD candidates of the Faculty of Arts (circa 250), and is committed to creating and maintaining excellent conditions for PhD research in all fields of the humanities. In addition to organizing local courses, the GSH works closely with 16 national research schools which offer regular courses and seminars by national and international top researchers.
The Centre for Language and Cognition of the University of Groningen (CLCG) is the institutional home for all the linguistic research carried out within the Faculty of Arts. The Computational Linguistics group of CLCG provides a vibrant working atmosphere with state-of-the-art research in all major areas of Natural Language Processing.
Recent advances of machine learning have led to substantial improvements in speech technology. These advances have mostly been focused on languages with many resources available, such as English. However, there are a gamut of compelling scientific challenges for lesser-resourced languages. In this project, the scope therefore will be on the regional language Frisian, which is spoken in the Northwest of the Netherlands. Specifically: (1) Frisian synthesis: building on existing approaches (e.g., those at Campus Fryslân), investigating techniques to improve the quality of the voice, and/or e.g., develop approaches to make the synthesis reflect the diversity of Frisian varieties, (2) Frisian automatic speech recognition (ASR): building on and improving existing approaches, also allowing for recognition of regional variety in Frisian, and/or (3) investigating the development of a search system for unlabelled acoustic Frisian data. The exact focus depends on the interests and background of the applicant, provided the focus is on speech technology for Frisian.
As the position will be integrated in the Speech Lab Groningen and the Center for Groningen Language and Culture at the Faculty of Arts, collaboration with other PhD students (Martijn Bartelds, Wietse de Vries) who are (partly) focusing on speech technology for the regional Groningen language variant is important for the project. To further benefit this project, it will be co-supervised by two experts on Frisian speech technology, D. Matt Coler at the Faculty Campus Fryslân, and Dr Jelske Dijkstra of the Fryske Akademy, both located in Leeuwarden. Collaboration with (PhD) student projects (such as those of Phat Do, Frank Hopwood, and Xiyuan Gao) conducted at these institutes is expected to benefit all involved projects. The project should contribute to infrastructure for speech technology for Frisian, specifically taking advantage of current projects on speech recognition and speech synthesis at Fryske Akademy and Campus Fryslân. To facilitate the integration in the two institutes in Leeuwarden, besides the main work place in Groningen, the candidate may spend a part of the week in Leeuwarden and would have a workspace at Campus Fryslân.
The successful applicant is committed to conducting independent and original scientific research focusing on the above field, to reporting on this research in international publications and presentations, and to presenting the final results of the research in a PhD dissertation. The PhD candidate will participate in local, national and international training activities, including summer schools and conferences, to maximally develop their potential.
As a member of the Graduate School for the Humanities, the PhD candidate may participate in courses, seminars and summer schools organized by Dutch national graduate school Landelijke Onderzoekschool Taalkunde (LOT) or by the Groningen Research School of Behavioural and Cognitive Neurosciences (BCN).
This PhD project offers a unique opportunity to work in an international research environment as well as to acquire valuable teaching experience: the PhD candidate is expected to conduct 0.3 FTE teaching during the second, third and fourth year of their appointment (0.1 FTE yearly).
We are looking for a PhD candidate who:
- has a relevant Master degree in for instance artificial intelligence, computer science, speech technology, human-machine interaction or a related field;
- has excellent programming skills (Python), and a strong interest in, or experience with, speech technology;
- has an interest in regional languages, including Frisian (it is not necessary to be able to speak Frisian, however);
- has excellent command of English (both oral and written) and good academic writing skills.
In accordance with the Collective Labour Agreement for Dutch Universities, the University of Groningen offers you:
- a salary of € 2,541 gross per month in the first year, up to a maximum of € 3,247 gross per month in the final year, based on a full-time position
- a holiday allowance of 8% gross annual income and an 8.3% end-of-the-year allowance
- a temporary 1.0 FTE appointment for a specified period of four years. The candidate will first be appointed for twelve months. After six months, an assessment will take place of the candidate’s results and the progress of the PhD project, in order to decide whether employment will be continued.
You will be enrolled in the Graduate School for the Humanities (GSH) of the Faculty of Arts at the University of Groningen. The GSH offers the organizational infrastructure within which PhD candidates participate in advanced training and supervised research: https://www.rug.nl/research/gradschool-humanities/
You will be carrying out your research in the context of the Neurolinguistics and Language Development group of the CLCG research institute.
The prospective starting date is 1 January 2023 at the latest