Vacancy – job opening: Postdoctoral ASR – Speech Researcher

on the project BLISS: Behaviour-based Language-Interactive Speaking Systems
New application deadline: 31 January 2019
To apply, click here, i.e. on
Your application should include (and be limited to): Letter of motivation, and CV.
See also

The Centre of Language and Speech Technology (CLST) at Radboud University has a vacancy for a post-doctoral researcher on the Behaviour-based Language-Interactive Speaking Systems (BLISS) project. BLISS is a project in the Data2Person programme of the Netherlands Organisation for Scientific Research (NWO). The BLISS project combines research on how data science can make a substantial contribution to self-management and improvement of the individual health situation with building an adaptive human-machine communication system. In this project we will build a smart, personal, spoken dialogue system (SDS) supporting self-management as a research platform that is able to meaningfully communicate with people in their native language about issues regarding their personal health, well-being and happiness through Automatic Speech Recognition (ASR). For this SDS we need to personalise the ASR component to adapt to speaker variation and to topic changes in dialogue. As a researcher you will combine deep knowledge of (Kaldi) speech recognition technology with experience in SDS. The research will be documented in scientific publications in appropriate journals and relevant conference proceedings, and in Open Source software tools.

Work environment
You will be hosted at the Centre of Language and Speech Technology (CLST), Radboud University, Nijmegen.
The Faculty of Arts consists of ten departments in the areas of Linguistics, Communication and Information Studies, Language and Culture, History, and History of arts, which together cater for about 2,400 students and collaborate closely in teaching and research. Research at the Faculty of Arts is embedded in two research institutes: the Centre for Language Studies (CLS), and the Institute for Historical, Literary and Cultural Studies (HLCS).

What we expect from you

  • A PhD in Engineering, Computer Science, Machine Learning, Signal Processing, Computational Linguistics or any other relevant discipline;
  • Experience in speech technology and/or spoken dialogue systems;
  • Preferably experience with the Kaldi speech recognition environment;
  • An excellent publication record;
  • Fluency in spoken and written English;
  • Preferably a good command of Dutch;
  • Experience with Linux OS, Git version control, scripting in Python;
  • Affinity with the open source community.

What we have to offer

  • employment: 0.5 – 0.8 FTE;
  • a maximum gross monthly salary of € 4,852 based on a 38-hour working week (salary scale 11);
  • in addition to the salary: an 8% holiday allowance and an 8.3% end-of-year bonus;
  • duration of the contract: starting from January 2019, you will be appointed as a Researcher for an initial period of 3 months, after which your performance will be evaluated. If the evaluation is positive, the contract will be extended to the end date, 1 August 2022;
  • classification in the Dutch university job-ranking system (UFO): Postdoctoral Researcher, Level 3;
  • you will be able to make use of our Dual Career Service where our Dual Career Officer will assist with family related support, such as child care, and help your partner prepare for the local labour market and with finding an occupation.

Would you like to know more?
Further information on: Centre for Language and Speech Technology (CLST)
Further information on: Faculty of Arts

For more information about this vacancy, please contact:
Mr Helmer Strik, E-mail: ‘w.strik -at-’, Tel.: +31 24 361 61 04
Mr Louis ten Bosch, E-mail: ‘l.tenbosch -at-’, Tel.: +31 24 361 60 69

Are you interested?
You should upload your application (attn. of mr M.J.M. van Nijnatten, head HRM Department Faculty of Arts) exclusively via
Your application should include (and be limited to): Letter of motivation, and CV.
No commercial propositions please.